# project: modelmap document: Bibliography author: Simon-Pierre Boucher contact: contact@spboucher.ai website: https://modelmap.io created: 2026-08-12 modified: 2026-08-12 status: draft

# Bibliography

Every consulted source, with URL and access date. Populated during Phase 1 (charter §4). Entries: - Authors — Title (year). URL — accessed YYYY-MM-DD. [theme tags] Duplicates across themes are listed once, under their primary theme. Entries flagged (spot-check) carry stable canonical IDs cited from memory by the survey pass and should be re-verified before citation in a published document.

# §4.1 — Observational probing

• Alain & Bengio — Understanding intermediate layers using linear classifier probes (2016). https://arxiv.org/abs/1610.01644 — accessed 2026-08-12. [probing]
• Belinkov — Probing Classifiers: Promises, Shortcomings, and Advances (2021/2022). https://arxiv.org/abs/2102.12452 ; https://aclanthology.org/2022.cl-1.7/ — accessed 2026-08-12. [probing, survey] (spot-check)
• Hewitt & Liang — Designing and Interpreting Probes with Control Tasks (2019). https://arxiv.org/abs/1909.03368 — accessed 2026-08-12. [probing, controls] (spot-check)
• Voita & Titov — Information-Theoretic Probing with Minimum Description Length (2020). https://arxiv.org/pdf/2003.12298 — accessed 2026-08-12. [probing, controls]
• nostalgebraist — interpreting GPT: the logit lens (2020). https://www.lesswrong.com/posts/AcKRB8wDpdaN6v6ru/interpreting-gpt-the-logit-lens — accessed 2026-08-12. [logit-lens]
• Belrose et al. — Eliciting Latent Predictions from Transformers with the Tuned Lens (2023). https://arxiv.org/abs/2303.08112 ; https://github.com/AlignmentResearch/tuned-lens — accessed 2026-08-12. [tuned-lens]
• Chuang et al. — DoLa: Decoding by Contrasting Layers (2023). https://arxiv.org/abs/2309.03883 — accessed 2026-08-12. [early-decoding]
• Pal et al. — Future Lens: Anticipating Subsequent Tokens from a Single Hidden State (2023). https://www.alphaxiv.org/overview/2311.04897v1 ; https://future.baulab.info/ — accessed 2026-08-12. [lens-successors]
• Ghandeharioun et al. — Patchscopes (2024). https://arxiv.org/abs/2401.06102 ; https://pair-code.github.io/interpretability/patchscopes/ — accessed 2026-08-12. [lens-successors]
• SimLens for Early Exit (2025). https://arxiv.org/pdf/2507.17618 — accessed 2026-08-12. [lens-successors, 2025]
• Zou et al. — Representation Engineering: A Top-Down Approach to AI Transparency (2023). https://arxiv.org/abs/2310.01405 ; https://github.com/andyzoujm/representation-engineering — accessed 2026-08-12. [RepE]
• Representation Engineering: Survey and Research Challenges (2025). https://arxiv.org/pdf/2502.17601 — accessed 2026-08-12. [RepE, critique]
• Vogel — repeng (control-vector library). https://github.com/vgel/repeng ; llama.cpp PR https://github.com/ggml-org/llama.cpp/pull/5970 — accessed 2026-08-12. [tooling, steering, GGUF]
• Ravfogel et al. — Null It Out: INLP (ACL 2020). https://aclanthology.org/2020.acl-main.647.pdf — accessed 2026-08-12. [concept-erasure]
• Elazar et al. — Amnesic Probing (TACL 2021). https://aclanthology.org/2021.tacl-1.10/ — accessed 2026-08-12. [concept-erasure]
• Belrose et al. — LEACE: Perfect linear concept erasure in closed form (2023). https://arxiv.org/abs/2306.03819 ; https://github.com/EleutherAI/concept-erasure ; https://blog.eleuther.ai/oracle-leace/ — accessed 2026-08-12. [concept-erasure]
• Nonlinear Concept Erasure: a Density Matching Approach (2025). https://arxiv.org/abs/2507.12341 — accessed 2026-08-12. [concept-erasure, 2025]
• Improving Causal Interventions in Amnesic Probing with Mean Projection or LEACE (2025). https://arxiv.org/html/2506.11673 — accessed 2026-08-12. [concept-erasure, critique]

# §4.2 — Causal / interventional methods

• Vig et al. — Investigating Gender Bias in LMs Using Causal Mediation Analysis (NeurIPS 2020). https://papers.nips.cc/paper/2020/hash/92650b2e92217715fe312e6fa7b90d82-Abstract.html — accessed 2026-08-12. [patching-origins]
• Zhang & Nanda — Towards Best Practices of Activation Patching (ICLR 2024). https://arxiv.org/abs/2309.16042 — accessed 2026-08-12. [patching, methodology]
• Heimersheim & Nanda — How to use and interpret activation patching (2024). https://arxiv.org/pdf/2404.15255 — accessed 2026-08-12. [patching, methodology]
• Nanda — How to Think About Activation Patching. https://www.alignmentforum.org/posts/xh85KbTFhbCz7taD4/how-to-think-about-activation-patching — accessed 2026-08-12. [patching]
• Goldowsky-Dill et al. — Localizing Model Behavior with Path Patching (2023). https://arxiv.org/abs/2304.05969 — accessed 2026-08-12. [path-patching]
• Nanda — Attribution Patching: Activation Patching At Industrial Scale (2023). https://www.neelnanda.io/mechanistic-interpretability/attribution-patching — accessed 2026-08-12. [attribution-patching]
• Syed, Rager, Conmy — Attribution Patching Outperforms Automated Circuit Discovery (BlackboxNLP 2024). https://aclanthology.org/2024.blackboxnlp-1.25.pdf ; https://arxiv.org/abs/2310.10348 — accessed 2026-08-12. [EAP]
• Kramár, Lieberum, Shah, Nanda — AtP*: efficient localization of LLM behaviour (2024). https://arxiv.org/abs/2403.00745 ; https://github.com/koayon/atp_star — accessed 2026-08-12. [attribution-patching]
• When Attribution Patching Lies (2026). https://arxiv.org/pdf/2606.09899 — accessed 2026-08-12. [attribution-patching, critique, 2026]
• RelP: Relevance Patching (2025). https://arxiv.org/html/2508.21258v1 — accessed 2026-08-12. [attribution-patching, 2025]
• Position-aware Automatic Circuit Discovery (2025). https://arxiv.org/pdf/2502.04577 — accessed 2026-08-12. [circuits, 2025]
• APP: Accelerated Path Patching (2025). https://arxiv.org/html/2511.05442 — accessed 2026-08-12. [path-patching, 2025]
• Chan et al. (Redwood) — Causal Scrubbing (2022). https://www.alignmentforum.org/posts/JvZhhzycHu2Yd57RN/causal-scrubbing-a-method-for-rigorously-testing ; appendix https://www.alignmentforum.org/posts/kcZZAsEjwrbczxN2i/causal-scrubbing-appendix — accessed 2026-08-12. [causal-scrubbing]
• Practical Pitfalls of Causal Scrubbing (2023). https://www.alignmentforum.org/posts/DFarDnQjMnjsKvW8s/practical-pitfalls-of-causal-scrubbing — accessed 2026-08-12. [causal-scrubbing, critique]
• Geiger et al. — Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations (DAS, CLeaR 2024). https://arxiv.org/abs/2303.02536 — accessed 2026-08-12. [DAS, IIA]
• Wu et al. — Interpretability at Scale: Boundless DAS in Alpaca (2023). https://arxiv.org/abs/2305.08809 — accessed 2026-08-12. [DAS]
• Wu et al. — pyvene (NAACL 2024). https://arxiv.org/abs/2403.07809 ; https://github.com/stanfordnlp/pyvene — accessed 2026-08-12. [tooling, DAS]
• Turner et al. — Steering Language Models With Activation Engineering (ActAdd, 2023). https://arxiv.org/abs/2308.10248 — accessed 2026-08-12. [steering]
• Rimsky et al. — Steering Llama 2 via Contrastive Activation Addition (ACL 2024). https://aclanthology.org/2024.acl-long.828/ ; https://arxiv.org/abs/2312.06681 — accessed 2026-08-12. [steering]
• Li et al. — Inference-Time Intervention (NeurIPS 2023). https://arxiv.org/pdf/2306.03341 — accessed 2026-08-12. [steering]
• Tan et al. — Analysing the Generalisation and Reliability of Steering Vectors (NeurIPS 2024). https://arxiv.org/abs/2407.12404 — accessed 2026-08-12. [steering, critique]
• Steering off Course: Reliability Challenges in Steering LMs (ACL 2025). https://aclanthology.org/2025.acl-long.974/ ; https://arxiv.org/html/2504.04635v1 — accessed 2026-08-12. [steering, critique, 2025]
• Understanding Unreliability of Steering Vectors (2026). https://arxiv.org/pdf/2602.17881 — accessed 2026-08-12. [steering, 2026]
• On the Non-Identifiability of Steering Vectors (2026). https://arxiv.org/pdf/2602.06801 — accessed 2026-08-12. [steering, 2026]
• The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching (2026). https://arxiv.org/html/2606.27510v1 — accessed 2026-08-12. [patching, critique, 2026]
• Bereska & Gavves — Mechanistic Interpretability for AI Safety: A Review (2024). https://arxiv.org/pdf/2404.14082 — accessed 2026-08-12. [survey]
• Fiotto-Kaufman et al. — NNsight and NDIF (ICLR 2025). https://arxiv.org/abs/2407.14561 ; https://github.com/ndif-team/nnsight ; https://ndif.us/ — accessed 2026-08-12. [tooling, remote-execution]
• Bau — baukit. https://github.com/davidbau/baukit — accessed 2026-08-12. [tooling]
• TransformerLens — Getting Started (MPS opt-in note). https://transformerlensorg.github.io/TransformerLens/content/getting_started.html ; https://github.com/TransformerLensOrg/TransformerLens — accessed 2026-08-12. [tooling, Apple-Silicon]
• IOI circuit in Mamba (2024). https://arxiv.org/html/2407.14008v1 — accessed 2026-08-12. [circuits, replication]

# §4.3 — Feature decomposition

• Elhage et al. — Toy Models of Superposition (2022). https://transformer-circuits.pub/2022/toy_model/index.html — accessed 2026-08-12. [superposition]
• Yun, Chen, Olshausen, LeCun — Transformer visualization via dictionary learning (2021). https://arxiv.org/abs/2103.15949 — accessed 2026-08-12. [dictionary-learning]
• Sharkey, Braun, Millidge — Interim report: taking features out of superposition with SAEs (2022). https://www.lesswrong.com/posts/z6QQJbtpkEAX3Aojj/interim-research-report-taking-features-out-of-superposition — accessed 2026-08-12. [SAE-precursor]
• Cunningham et al. — Sparse Autoencoders Find Highly Interpretable Features in LMs (2023). https://arxiv.org/abs/2309.08600 — accessed 2026-08-12. [SAE]
• Bricken et al. — Towards Monosemanticity (2023). https://transformer-circuits.pub/2023/monosemantic-features/index.html — accessed 2026-08-12. [SAE, feature-splitting]
• Templeton et al. — Scaling Monosemanticity (2024). https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html — accessed 2026-08-12. [SAE-scaling, pipeline, feature-browser]
• Rajamanoharan et al. — Gated Sparse Autoencoders (2024). https://arxiv.org/abs/2404.16014 — accessed 2026-08-12. [SAE-variant]
• Gao et al. — Scaling and evaluating sparse autoencoders (TopK, 2024). https://arxiv.org/abs/2406.04093 — accessed 2026-08-12. [SAE-variant]
• Rajamanoharan et al. — JumpReLU Sparse Autoencoders (2024). https://arxiv.org/abs/2407.14435 — accessed 2026-08-12. [SAE-variant]
• Bussmann, Leask, Nanda — BatchTopK Sparse Autoencoders (2024). https://arxiv.org/abs/2412.06410 — accessed 2026-08-12. [SAE-variant]
• Bussmann et al. — Matryoshka Sparse Autoencoders (2025). https://arxiv.org/abs/2503.17547 — accessed 2026-08-12. [SAE-variant, absorption]
• Lindsey et al. — Sparse Crosscoders for Cross-Layer Features and Model Diffing (2024). https://transformer-circuits.pub/2024/crosscoders/index.html — accessed 2026-08-12. [crosscoders]
• Dunefsky, Chlenski, Nanda — Transcoders Find Interpretable LLM Feature Circuits (2024). https://arxiv.org/abs/2406.11944 — accessed 2026-08-12. [transcoders]
• Paulo, Shabalin, Belrose — Transcoders Beat Sparse Autoencoders for Interpretability (2025). https://arxiv.org/abs/2501.18823 — accessed 2026-08-12. [skip-transcoders]
• Chanin et al. — A is for Absorption (2024). https://arxiv.org/abs/2409.14507 — accessed 2026-08-12. [feature-absorption]
• Engels et al. — Not All Language Model Features Are Linear (2024). https://arxiv.org/abs/2405.14860 — accessed 2026-08-12. [feature-geometry]
• Bills et al. — Language models can explain neurons in language models (2023). https://openaipublic.blob.core.windows.net/neuron-explainer/paper/index.html — accessed 2026-08-12. [auto-interp]
• Paulo et al. — Automatically Interpreting Millions of Features (2024). https://arxiv.org/abs/2410.13928 — accessed 2026-08-12. [auto-interp]
• Huang et al. — Rigorously Assessing Natural Language Explanations of Neurons (2023). https://arxiv.org/abs/2309.10312 — accessed 2026-08-12. [auto-interp-critique]
• Karvonen et al. — SAEBench (2025). https://arxiv.org/abs/2503.09532 ; https://www.neuronpedia.org/sae-bench/info ; https://github.com/adamkarvonen/SAEBench — accessed 2026-08-12. [SAE-evaluation]
• Chanin et al. — Are Sparse Autoencoder Benchmarks Reliable? (2026). https://arxiv.org/abs/2605.18229 — accessed 2026-08-12. [evaluation-critique, 2026]
• Smith et al. (GDM) — Negative Results for SAEs On Downstream Tasks and Deprioritising SAE Research (2025). https://deepmindsafetyresearch.medium.com/negative-results-for-sparse-autoencoders-on-downstream-tasks-and-deprioritising-sae-research-6cadcfc125b9 — accessed 2026-08-12. [SAE-debate]
• Kantamneni et al. — Are Sparse Autoencoders Useful? A Case Study in Sparse Probing (2025). https://arxiv.org/abs/2502.16681 — accessed 2026-08-12. [SAE-debate]
• Wu et al. — AxBench (2025). https://arxiv.org/abs/2501.17148 — accessed 2026-08-12. [steering, SAE-debate]
• Kissane et al. — SAEs are highly dataset dependent (2024). https://www.alignmentforum.org/posts/rtp6n7Z23uJpEH7od/saes-are-highly-dataset-dependent-a-case-study-on-the — accessed 2026-08-12. [dataset-dependence]
• Paulo, Belrose — SAEs Trained on the Same Data Learn Different Features (2025). https://arxiv.org/abs/2501.16615 — accessed 2026-08-12. [seed-dependence, replication]
• Movva et al. — Use SAEs to Discover Unknown Concepts, Not to Act on Known Concepts (2025). https://arxiv.org/abs/2506.23845 — accessed 2026-08-12. [SAE-debate]
• Lieberum et al. — Gemma Scope (2024). https://arxiv.org/abs/2408.05147 ; https://huggingface.co/google/gemma-scope — accessed 2026-08-12. [open-SAEs, artifacts]
• He et al. — Llama Scope (2024). https://arxiv.org/abs/2410.20526 — accessed 2026-08-12 (spot-check). [open-SAEs]
• Huang et al. — RAVEL (ACL 2024). https://arxiv.org/abs/2402.17700 ; https://github.com/explanare/ravel — accessed 2026-08-12. [evaluation, causal]
• CE-Bench (2025). https://arxiv.org/abs/2509.00691 — accessed 2026-08-12. [SAE-evaluation, 2025]
• SynthSAEBench (2026). https://arxiv.org/abs/2602.14687 — accessed 2026-08-12. [SAE-evaluation, synthetic, 2026]
• SAELens (Bloom, Tigges, Chanin et al.). https://github.com/jbloomAus/SAELens ; https://github.com/decoderesearch/SAELens — accessed 2026-08-12. [tooling, MPS]
• dictionary_learning (Marks, Mueller). https://github.com/saprmarks/dictionary_learning — accessed 2026-08-12. [tooling]
• EleutherAI — sparsify. https://github.com/EleutherAI/sparsify — accessed 2026-08-12. [tooling, streaming]
• EleutherAI — delphi (auto-interp). https://github.com/EleutherAI/delphi — accessed 2026-08-12. [tooling]
• EleutherAI — clt-training. https://github.com/EleutherAI/clt-training — accessed 2026-08-12. [tooling, CLT]
• ckkissane — crosscoder-model-diff-replication. https://github.com/ckkissane/crosscoder-model-diff-replication — accessed 2026-08-12. [tooling]

# §4.4 — Circuits and computational graphs

• Olsson et al. — In-context Learning and Induction Heads (2022). https://transformer-circuits.pub/2022/in-context-learning-and-induction-heads/index.html ; https://arxiv.org/abs/2209.11895 — accessed 2026-08-12. [induction-heads, universality]
• Wang et al. — Interpretability in the Wild: IOI circuit (2022). https://arxiv.org/abs/2211.00593 — accessed 2026-08-12. [IOI, circuits, path-patching]
• McDougall et al. — Copy Suppression (2023). https://arxiv.org/abs/2310.04625 — accessed 2026-08-12. [head-taxonomy]
• Gould et al. — Successor Heads (2023). https://arxiv.org/abs/2312.09230 — accessed 2026-08-12. [head-taxonomy, universality]
• McGrath et al. — The Hydra Effect (2023). https://arxiv.org/abs/2307.15771 — accessed 2026-08-12. [self-repair, ablation-critique]
• Geva et al. — Transformer Feed-Forward Layers Are Key-Value Memories (2021). https://arxiv.org/abs/2012.14913 — accessed 2026-08-12. [MLP-KV]
• Geva et al. — FFN Layers Build Predictions by Promoting Concepts in Vocabulary Space (2022). https://arxiv.org/abs/2203.14680 — accessed 2026-08-12. [MLP-KV]
• Ameisen, Lindsey et al. — Circuit Tracing: Revealing Computational Graphs (2025). https://transformer-circuits.pub/2025/attribution-graphs/methods.html — accessed 2026-08-12. [attribution-graphs]
• Lindsey et al. — On the Biology of a Large Language Model (2025). https://transformer-circuits.pub/2025/attribution-graphs/biology.html — accessed 2026-08-12. [attribution-graphs]
• Anthropic — Tracing Attention Computation Through Feature Interactions (2025). https://transformer-circuits.pub/2025/attention-qk/index.html — accessed 2026-08-12. [QK-attribution]
• Anthropic — Open-sourcing circuit-tracing tools (2025). https://www.anthropic.com/research/open-source-circuit-tracing — accessed 2026-08-12. [circuit-tracer]
• Hanna, Piotrowski et al. — circuit-tracer (2025). https://github.com/safety-research/circuit-tracer ; https://github.com/decoderesearch/circuit-tracer ; https://aclanthology.org/2025.blackboxnlp-1.14.pdf — accessed 2026-08-12. [tooling]
• Conmy et al. — Towards Automated Circuit Discovery (ACDC, NeurIPS 2023). https://arxiv.org/abs/2304.14997 ; https://github.com/ArthurConmy/Automatic-Circuit-Discovery — accessed 2026-08-12. [circuit-discovery]
• Hanna, Pezzelle, Belinkov — Have Faith in Faithfulness (EAP-IG, COLM 2024). https://arxiv.org/abs/2403.17806 ; https://github.com/hannamw/EAP-IG — accessed 2026-08-12. [EAP-IG, faithfulness]
• Bhaskar et al. — Finding Transformer Circuits with Edge Pruning (NeurIPS 2024). https://arxiv.org/abs/2406.16778 ; https://github.com/princeton-nlp/Edge-Pruning — accessed 2026-08-12. [edge-pruning]
• Miller, Chughtai, Saunders — Transformer Circuit Faithfulness Metrics are not Robust (2024). https://arxiv.org/abs/2407.08734 — accessed 2026-08-12. [faithfulness-critique]
• Shi et al. — Hypothesis Testing the Circuit Hypothesis (NeurIPS 2024). https://arxiv.org/abs/2410.13032 ; https://github.com/blei-lab/circuitry — accessed 2026-08-12. [faithfulness, statistics]
• Marks et al. — Sparse Feature Circuits (ICLR 2025). https://arxiv.org/abs/2403.19647 ; https://github.com/saprmarks/feature-circuits — accessed 2026-08-12. [feature-circuits, SHIFT]
• Gao, Rajaram et al. (OpenAI) — Weight-sparse transformers have interpretable circuits (2025). https://arxiv.org/abs/2511.13653 ; https://github.com/openai/circuit_sparsity — accessed 2026-08-12. [weight-sparsity]
• Interpretable individual parameters follow-up (2026). https://arxiv.org/abs/2607.02964 — accessed 2026-08-12. [weight-sparsity, 2026]
• ADAG — Automatically Describing Attribution Graphs (2026). https://arxiv.org/abs/2604.07615 — accessed 2026-08-12. [automation, 2026]
• Circuit Insights: Towards Interpretability Beyond Activations (2025). https://arxiv.org/abs/2510.14936 — accessed 2026-08-12. [weight-based, 2025]
• Anthropic — Circuits Updates June 2026. https://transformer-circuits.pub/2026/june-update/index.html — accessed 2026-08-12. [2026, safety-auditing]
• Neuronpedia — Circuits Research Landscape (Aug 2025). https://www.neuronpedia.org/graph/info — accessed 2026-08-12. [community, attribution-graphs]
• UFO-101 — auto-circuit (multi-ablation library). https://github.com/UFO-101/auto-circuit — accessed 2026-08-12. [tooling, ablations]
• anthropics — attribution-graphs-frontend. https://github.com/anthropics/attribution-graphs-frontend — accessed 2026-08-12. [tooling, viz]
• mlxterp — Mechanistic Interpretability Library for Apple Silicon (COAI). https://github.com/coairesearch/mlxterp — accessed 2026-08-12. [tooling, MLX, Apple-Silicon]

# §4.5 — Weight-space cartography

• Sharma, Ash, Misra — The Truth is in There: LASER (ICLR 2024). https://arxiv.org/abs/2312.13558 ; https://github.com/pratyushasharma/laser — accessed 2026-08-12. [weight-SVD, intervention]
• Martin & Mahoney — Heavy-Tailed Universality Predicts Trends in Test Accuracies (2019). https://arxiv.org/abs/1901.08278 — accessed 2026-08-12. [weight-only, spectra]
• Martin, Peng, Mahoney — Predicting NN quality without training/testing data (2020). https://arxiv.org/abs/2002.06716 — accessed 2026-08-12. [weight-only, pre-screen-prior-art]
• WeightWatcher. https://github.com/CalculatedContent/WeightWatcher — accessed 2026-08-12. [tooling, Mac-native]
• Martin & Mahoney — Post-mortem: Simpson's paradox in weight metrics (2021). https://arxiv.org/abs/2106.00734 — accessed 2026-08-12. [critique]
• Dettmers et al. — LLM.int8() (2022). https://arxiv.org/abs/2208.07339 — accessed 2026-08-12. [outliers]
• Sun, Chen, Kolter, Liu — Massive Activations in LLMs (2024). https://arxiv.org/abs/2402.17762 — accessed 2026-08-12. [outliers, sinks]
• Xiao et al. — Attention Sinks / StreamingLLM (2023). https://arxiv.org/abs/2309.17453 — accessed 2026-08-12. [sinks]
• Gu et al. — When Attention Sink Emerges (2024). https://arxiv.org/abs/2410.10781 — accessed 2026-08-12. [sinks]
• Yu et al. — The Super Weight in LLMs (2024). https://arxiv.org/abs/2411.07191 ; https://machinelearning.apple.com/research/the-super-weight — accessed 2026-08-12. [weight-visible-outliers, causal]
• Attention Sink in Transformers: A Survey (2026). https://arxiv.org/pdf/2604.10098 — accessed 2026-08-12. [sinks, 2026]
• A Single Layer to Explain Them All: Massive Activations (2026). https://arxiv.org/html/2605.08504 — accessed 2026-08-12. [outliers, 2026]
• Kornblith et al. — CKA (2019). https://arxiv.org/abs/1905.00414 — accessed 2026-08-12 (spot-check). [similarity]
• Raghu et al. — SVCCA (2017). https://arxiv.org/abs/1706.05806 — accessed 2026-08-12 (spot-check). [similarity]
• Davari et al. — Reliability of CKA (ICLR 2023). https://arxiv.org/abs/2210.16156 — accessed 2026-08-12. [CKA-pathologies]
• Ding, Denain, Steinhardt — Grounding Representation Similarity with Statistical Testing (2021). https://arxiv.org/abs/2108.01661 — accessed 2026-08-12. [similarity-critique]
• Projection kernel between attention-head weight subspaces (2026). https://arxiv.org/pdf/2601.10266 — accessed 2026-08-12. [weight-only-similarity, 2026]
• Gromov et al. — The Unreasonable Ineffectiveness of the Deeper Layers (2024). https://arxiv.org/abs/2403.17887 — accessed 2026-08-12. [layer-redundancy]
• Men et al. — ShortGPT (2024). https://arxiv.org/abs/2403.03853 — accessed 2026-08-12. [layer-redundancy]
• Lenc & Vedaldi — Equivariance and equivalence (2015). https://arxiv.org/abs/1411.5908 — accessed 2026-08-12. [stitching]
• Bansal, Nakkiran, Barak — Revisiting Model Stitching (2021). https://arxiv.org/abs/2106.07682 — accessed 2026-08-12. [stitching]
• Ainsworth et al. — Git Re-Basin (ICLR 2023). https://arxiv.org/abs/2209.04836 ; https://github.com/samuela/git-re-basin — accessed 2026-08-12. [permutation-alignment]
• Jordan et al. — REPAIR (2022). https://arxiv.org/abs/2211.08403 — accessed 2026-08-12. [permutation-alignment]
• Peña et al. — Re-basin via implicit Sinkhorn differentiation (2022). https://arxiv.org/abs/2212.12042 — accessed 2026-08-12. [permutation-alignment]
• Sharma et al. — Simultaneous linear connectivity modulo permutation (2024). https://arxiv.org/abs/2404.06498 — accessed 2026-08-12. [mode-connectivity]
• Garipov et al. — Loss Surfaces, Mode Connectivity, Fast Ensembling (2018). https://arxiv.org/abs/1802.10026 — accessed 2026-08-12. [mode-connectivity]
• Frankle et al. — Linear Mode Connectivity and the Lottery Ticket Hypothesis (2019). https://arxiv.org/abs/1912.05671 — accessed 2026-08-12. [mode-connectivity]
• Entezari et al. — Role of permutation invariance in linear mode connectivity (2021). https://arxiv.org/abs/2110.06296 — accessed 2026-08-12. [mode-connectivity]
• Lubana et al. — Mechanistic Mode Connectivity (2022). https://arxiv.org/abs/2211.08422 — accessed 2026-08-12. [mode-connectivity]
• Ilharco et al. — Editing Models with Task Arithmetic (ICLR 2023). https://arxiv.org/abs/2212.04089 ; https://github.com/mlfoundations/task_vectors — accessed 2026-08-12. [task-vectors]
• Yadav et al. — TIES-Merging (2023). https://arxiv.org/abs/2306.01708 — accessed 2026-08-12. [delta-analysis]
• Yu et al. — DARE (2023). https://arxiv.org/abs/2311.03099 — accessed 2026-08-12. [delta-sparsity]
• Minder et al. — Overcoming Sparsity Artifacts in Crosscoders (2025). https://arxiv.org/abs/2504.02922 — accessed 2026-08-12. [model-diffing, pitfalls]
• Anthropic — Stage-Wise Model Diffing (2024). https://transformer-circuits.pub/2024/model-diffing/index.html — accessed 2026-08-12. [model-diffing]
• Anthropic — Insights on Crosscoder Model Diffing (2025). https://transformer-circuits.pub/2025/crosscoder-diffing-update/index.html — accessed 2026-08-12. [model-diffing]
• Narrow Finetuning Leaves Clearly Readable Traces (2025). https://arxiv.org/abs/2510.13900 — accessed 2026-08-12. [model-diffing, 2025]
• Cross-Architecture Model Diffing with Crosscoders (2026). https://arxiv.org/pdf/2602.11729 — accessed 2026-08-12. [model-diffing, 2026]
• What We Learned Trying to Diff Base and Chat Models (LessWrong, 2025). https://www.lesswrong.com/posts/xmpauEXEerzYcJKNm/what-we-learned-trying-to-diff-base-and-chat-models-and-why — accessed 2026-08-12. [diffing-post-mortem]
• Watch the Weights: Unsupervised Monitoring of Fine-tuned LLMs (2025). https://arxiv.org/pdf/2508.00161 — accessed 2026-08-12. [weight-only, 2025]
• Learning to Interpret Weight Differences (2025). https://arxiv.org/html/2510.05092v4 — accessed 2026-08-12. [weight-diff, 2025]
• Steering LMs with Weight Arithmetic (Alignment Forum, 2025). https://www.alignmentforum.org/posts/HYTbakdHpxfaCowYp/steering-language-models-with-weight-arithmetic — accessed 2026-08-12. [weight-only-steering, 2025]
• Jiang et al. — Mixtral of Experts (2024). https://arxiv.org/abs/2401.04088 — accessed 2026-08-12. [MoE-routing]
• Dai et al. — DeepSeekMoE (2024). https://arxiv.org/abs/2401.06066 — accessed 2026-08-12. [MoE-structure]
• The Myth of Expert Specialization in MoEs (2026). https://arxiv.org/html/2604.09780v1 — accessed 2026-08-12. [MoE-critique, 2026]
• Unterthiner et al. — Predicting NN Accuracy from Weights (2020). https://arxiv.org/abs/2002.11448 — accessed 2026-08-12. [weights-as-data]
• Eilertsen et al. — Classifying the classifier (2020). https://arxiv.org/abs/2002.05688 — accessed 2026-08-12. [weights-as-data]
• Schürholt — hyper-representations publications. https://kschuerholt.github.io/publications/ — accessed 2026-08-12. [weight-space-learning]
• ICLR 2025 Workshop on Weight Space Learning. https://weight-space-learning.github.io/ — accessed 2026-08-12. [weight-space-learning, 2025]
• WeightCLIP / survey of weight space learning (2026). https://arxiv.org/html/2607.03551v1 — accessed 2026-08-12. [weight-space-learning, 2026]

# §4.6 — Knowledge localization and editing

• Meng, Bau, Andonian, Belinkov — Locating and Editing Factual Associations in GPT (ROME, NeurIPS 2022). https://arxiv.org/abs/2202.05262 ; https://rome.baulab.info/ ; https://github.com/kmeng01/rome — accessed 2026-08-12. [causal-tracing, editing]
• Meng et al. — MEMIT: Mass-Editing Memory in a Transformer (ICLR 2023). https://arxiv.org/abs/2210.07229 ; https://github.com/kmeng01/memit — accessed 2026-08-12. [mass-editing]
• Li et al. — PMET (AAAI 2024). https://arxiv.org/abs/2308.08742 — accessed 2026-08-12. [editing]
• Gupta et al. — EMMET / A Unified Framework for Model Editing (EMNLP Findings 2024). https://arxiv.org/abs/2403.14236 — accessed 2026-08-12. [editing-theory]
• Fang et al. — AlphaEdit (ICLR 2025 Outstanding Paper). https://arxiv.org/abs/2410.02355 ; https://github.com/jianghoucheng/alphaedit — accessed 2026-08-12. [editing, 2025]
• Reproducibility Study of AlphaEdit (2026). https://arxiv.org/pdf/2606.26783 — accessed 2026-08-12. [editing, 2026]
• UltraEdit — lifelong editing (2025). https://arxiv.org/abs/2505.14679 — accessed 2026-08-12. [lifelong-editing, 2025]
• Efficient Knowledge Editing via Minimal Precomputation (2025). https://arxiv.org/pdf/2506.04226 — accessed 2026-08-12. [editing-cost, 2025]
• Dai et al. — Knowledge Neurons in Pretrained Transformers (ACL 2022). https://arxiv.org/abs/2104.08696 — accessed 2026-08-12. [knowledge-neurons]
• Chen et al. — Journey to the Center of the Knowledge Neurons (2023). https://arxiv.org/html/2308.13198 — accessed 2026-08-12. [multilingual-neurons, critique]
• Neuron-Level Knowledge Attribution in LLMs (EMNLP 2024). https://arxiv.org/abs/2312.12141 — accessed 2026-08-12. [attribution-critique]
• Geva et al. — Dissecting Recall of Factual Associations (EMNLP 2023). https://arxiv.org/abs/2304.14767 — accessed 2026-08-12. [fact-recall-circuit]
• Hernandez et al. — Linearity of Relation Decoding / attribute lens (ICLR 2024). https://arxiv.org/abs/2308.09124 — accessed 2026-08-12. [attribute-lens]
• Chughtai, Cooney, Nanda — Summing Up the Facts (2024). https://arxiv.org/abs/2402.07321 — accessed 2026-08-12. [fact-recall-mechanisms]
• Hase et al. — Does Localization Inform Editing? (NeurIPS 2023). https://arxiv.org/abs/2301.04213 — accessed 2026-08-12. [localization-critique]
• Cohen et al. — Evaluating the Ripple Effects of Knowledge Editing (TACL 2024). https://arxiv.org/abs/2307.12976 — accessed 2026-08-12. [ripple-effects]
• Pressure-aware joint neighborhood optimization for ripple effects (2026). https://arxiv.org/pdf/2606.01610 — accessed 2026-08-12. [ripple-effects, 2026]
• Gupta, Rao, Anumanchipalli — Model Editing at Scale Leads to Gradual and Catastrophic Forgetting (2024). https://arxiv.org/abs/2401.07453 — accessed 2026-08-12. [sequential-collapse]
• Gupta et al. — Rebuilding ROME (2024). https://arxiv.org/abs/2403.07175 — accessed 2026-08-12. [collapse-diagnosis]
• Gu et al. — Model Editing Harms General Abilities of LLMs (EMNLP 2024). https://arxiv.org/abs/2401.04700 — accessed 2026-08-12. [side-effects]
• Should We Really Edit Language Models? (2024). https://arxiv.org/pdf/2410.18785 — accessed 2026-08-12. [evaluation-critique]
• Energy-Regularized Sequential Model Editing on Hyperspheres (2025). https://arxiv.org/html/2510.01172v1 — accessed 2026-08-12. [lifelong-editing, 2025]
• Wang et al. — Cross-Lingual Knowledge Editing in LLMs (2023). https://arxiv.org/abs/2309.08952 — accessed 2026-08-12. [multilingual-editing]
• MPN: Multilingual Patch Neuron (2024). https://arxiv.org/abs/2401.03190 — accessed 2026-08-12. [multilingual-editing]
• Multilingual Knowledge Editing with Language-Agnostic Factual Neurons (2024). https://arxiv.org/abs/2406.16416 — accessed 2026-08-12. [multilingual-neurons]
• How Do Multilingual Language Models Remember Facts? (2024). https://arxiv.org/abs/2410.14387 — accessed 2026-08-12. [multilingual-recall]
• Paths Not Taken: Multilingual Factual Recall Pipeline (2025). https://arxiv.org/html/2505.20546v2 — accessed 2026-08-12. [multilingual-circuits, 2025]
• Editing Across Languages: Survey of Multilingual Knowledge Editing (EMNLP 2025). https://arxiv.org/html/2505.14393 — accessed 2026-08-12. [survey, 2025]
• Wang et al. — Knowledge Editing for LLMs: A Survey (2023). https://arxiv.org/pdf/2310.16218 — accessed 2026-08-12. [survey]
• Zhang et al. — A Comprehensive Study of Knowledge Editing for LLMs (2024). https://arxiv.org/pdf/2401.01286 — accessed 2026-08-12. [survey]
• zjunlp/EasyEdit (ACL 2024). https://github.com/zjunlp/EasyEdit — accessed 2026-08-12. [tooling, CUDA-first]

# §4.7 — Cross-model and cross-scale comparison

• Klabunde et al. — Similarity of Neural Network Models: A Survey (2023, rev. 2025). https://arxiv.org/abs/2305.06329 — accessed 2026-08-12. [similarity, survey]
• Klabunde et al. — Towards Measuring Representational Similarity of LLMs (2023). https://arxiv.org/abs/2312.02730 — accessed 2026-08-12. [similarity, LLM]
• Klabunde, Wald et al. — ReSi: A Comprehensive Benchmark for Representational Similarity Measures (ICLR 2025). https://arxiv.org/abs/2408.00531 — accessed 2026-08-12. [similarity, benchmark]
• Gurnee et al. — Universal Neurons in GPT2 Language Models (2024). https://arxiv.org/abs/2401.12181 — accessed 2026-08-12. [universality, neurons]
• Universal Neurons in GPT-2: Emergence, Persistence, and Functional Impact (2025). https://arxiv.org/abs/2508.00903 — accessed 2026-08-12. [universality, 2025]
• Crosbie & Shutova — Induction Heads as an Essential Mechanism for Pattern Matching in ICL (2024). https://arxiv.org/abs/2407.07011 — accessed 2026-08-12. [universality, circuits]
• Wang et al. — Towards Universality: Mechanistic Similarity Across Architectures (2024). https://arxiv.org/abs/2410.06672 — accessed 2026-08-12. [universality, cross-architecture]
• Universal Response and Emergence of Induction in LLMs (2024). https://arxiv.org/abs/2411.07071 — accessed 2026-08-12. [universality]
• Lieberum et al. — Does Circuit Analysis Interpretability Scale? Chinchilla 70B (2023). https://arxiv.org/abs/2307.09458 — accessed 2026-08-12. [cross-scale, circuits]
• Tigges et al. — LLM Circuit Analyses Are Consistent Across Training and Scale (2024). https://arxiv.org/abs/2407.10827 — accessed 2026-08-12. [cross-scale, circuits]
• Lan et al. — Quantifying Feature Space Universality Across LLMs via SAEs (2024/2025). https://arxiv.org/abs/2410.06981 — accessed 2026-08-12. [universality, SAE]
• Thasarathan et al. — Universal Sparse Autoencoders (2025). https://arxiv.org/abs/2502.03714 — accessed 2026-08-12. [universality, SAE]
• Open-source replication of Anthropic's crosscoder paper (LessWrong). https://www.lesswrong.com/posts/srt6JXsRMtmqAJavD/open-source-replication-of-anthropic-s-crosscoder-paper-for — accessed 2026-08-12. [crosscoders, replication]
• Huh, Cheung, Wang, Isola — The Platonic Representation Hypothesis (ICML 2024). https://arxiv.org/abs/2405.07987 — accessed 2026-08-12. [PRH]
• Ziyin et al. — Proof of a Perfect Platonic Representation Hypothesis (2025). https://arxiv.org/abs/2507.01098 — accessed 2026-08-12. [PRH, theory]
• Revisiting the Platonic Representation Hypothesis: An Aristotelian View (2026). https://arxiv.org/abs/2602.14486 — accessed 2026-08-12. [PRH, critique, 2026]
• Causes and Consequences of Representational Similarity in ML Models (2025). https://arxiv.org/pdf/2505.13899 — accessed 2026-08-12. [similarity, convergence]
• Model Stitching: Looking For Functional Similarity Between Representations (2023). https://arxiv.org/abs/2303.11277 — accessed 2026-08-12. [stitching]
• How Not to Stitch Representations to Measure Similarity (2024). https://arxiv.org/pdf/2412.11299 — accessed 2026-08-12. [stitching, pitfalls]
• Moschella et al. line — Latent Communication in Artificial Neural Networks (2024). https://arxiv.org/pdf/2406.11014 — accessed 2026-08-12. [relative-representations]
• Dravid, Gandelsman, Efros, Shocher — Rosetta Neurons (ICCV 2023). https://arxiv.org/abs/2306.09346 ; https://github.com/yossigandelsman/rosetta_neurons — accessed 2026-08-12. [universality, vision]
• TokSuite: Measuring the Impact of Tokenizer Choice on LM Behavior (2025). https://arxiv.org/pdf/2512.20757 — accessed 2026-08-12. [tokenizers]
• Minixhofer, Vulić, Ponti — Cross-Tokenizer Distillation via Approximate Likelihood Matching (2025). https://arxiv.org/abs/2503.20083 — accessed 2026-08-12. [tokenizers]
• Tokenisation is NP-Complete (2024). https://arxiv.org/pdf/2412.15210 — accessed 2026-08-12. [tokenizers]
• Interpreting the Effects of Quantization on LLMs (IJCNLP-AACL 2025). https://arxiv.org/abs/2508.16785 — accessed 2026-08-12. [quantization, interpretability]
• Through a Compressed Lens: Impact of Quantization on LLM Explainability and Interpretability (2025). https://arxiv.org/abs/2505.13963 — accessed 2026-08-12. [quantization, interpretability]
• How Quantization Changes Interpretable Features: An SAE Analysis of LMs (2026). https://arxiv.org/html/2606.03002v1 — accessed 2026-08-12. [quantization, SAE, 2026]
• The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs (2026). https://arxiv.org/pdf/2607.08734 — accessed 2026-08-12. [quantization, statistics, 2026]
• Does Quantization Affect Models' Performance on Long-Context Tasks? (2025). https://arxiv.org/pdf/2505.20276 — accessed 2026-08-12. [quantization, behavior]

# §4.8 — Statistics and epistemology of interpretability

• Bolukbasi et al. — An Interpretability Illusion for BERT (2021). https://arxiv.org/abs/2104.07143 — accessed 2026-08-12. [illusions, dataset-sensitivity]
• Makelov, Lange, Nanda — Is This the Subspace You Are Looking For? (2023). https://arxiv.org/abs/2311.17030 — accessed 2026-08-12. [illusions, patching]
• Wu et al. — A Reply to Makelov et al.'s "Interpretability Illusion" Arguments (2024). https://arxiv.org/abs/2401.12631 ; https://www.alphaxiv.org/abs/2401.12631 — accessed 2026-08-12. [illusions, debate]
• Friedman, Lampinen, Dixon, Chen, Ghandeharioun — Interpretability Illusions in the Generalization of Simplified Models (ICML 2024). https://arxiv.org/abs/2312.03656 — accessed 2026-08-12. [illusions, OOD]
• Jacovi & Goldberg — Towards Faithfully Interpretable NLP Systems (ACL 2020). https://arxiv.org/abs/2004.03685 — accessed 2026-08-12 (spot-check). [faithfulness]
• The Dead Salmons of AI Interpretability (2025). https://arxiv.org/abs/2512.18792 — accessed 2026-08-12. [statistics, multiplicity, 2025]
• Bennett et al. — Neural Correlates of Interspecies Perspective Taking in the Post-Mortem Atlantic Salmon (2009). https://prefrontal.org/files/posters/Bennett-Salmon-2009.pdf — accessed 2026-08-12. [statistics, historical]
• Lindner et al. — Tracr: Compiled Transformers as a Laboratory for Interpretability (NeurIPS 2023). https://arxiv.org/abs/2301.05062 ; https://github.com/google-deepmind/tracr — accessed 2026-08-12 (spot-check). [benchmark, ground-truth]
• Gupta et al. — InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability (NeurIPS 2024 D&B). https://arxiv.org/abs/2407.14494 — accessed 2026-08-12. [benchmark, ground-truth]
• Mueller, Geiger et al. — MIB: A Mechanistic Interpretability Benchmark (ICML 2025). https://arxiv.org/abs/2504.13151 — accessed 2026-08-12. [benchmark, 2025]
• BlackboxNLP-2025 MIB Shared Task (2025). https://arxiv.org/html/2510.06811v1 — accessed 2026-08-12. [benchmark, 2025]
• Geiger et al. — Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability (JMLR 2025). https://arxiv.org/abs/2301.04709 — accessed 2026-08-12. [causal-abstraction, theory]
• The Non-Linear Representation Dilemma: Is Causal Abstraction Enough? (2025). https://arxiv.org/abs/2507.08802 — accessed 2026-08-12. [causal-abstraction, critique, 2025]
• Saphra & Wiegreffe — Mechanistic? (BlackboxNLP 2024). https://arxiv.org/abs/2410.09087 — accessed 2026-08-12. [epistemology, position]
• Casper — The Engineer's Interpretability Sequence (2023). https://www.alignmentforum.org/s/a6ne2ve5uturEEQK7 — accessed 2026-08-12. [rigor, position]
• Sharkey, Chughtai, Batson, Lindsey et al. — Open Problems in Mechanistic Interpretability (2025). https://arxiv.org/abs/2501.16496 — accessed 2026-08-12. [rigor, survey, 2025]
• Williams, Oldenburg et al. — Mechanistic Interpretability Needs Philosophy (2025). https://arxiv.org/abs/2506.18852 — accessed 2026-08-12. [epistemology, 2025]
• Make Mechanistic Interpretability Auditable (ACL 2026). https://arxiv.org/pdf/2606.00033 — accessed 2026-08-12. [rigor, auditing, 2026]

# §4.9 — Systems side (local mapping at scale)

• safetensors contributors — safetensors. https://github.com/safetensors/safetensors — accessed 2026-08-12. [storage]
• zarr-developers — zarr-python performance discussion. https://lightrun.com/answers/zarr-developers-zarr-python-zarr-slower-than-npy-hdf5-etc — accessed 2026-08-12. [storage, benchmarks]
• h5py. https://www.h5py.org/ — accessed 2026-08-12. [storage]
• SAELens training docs (ActivationsStore, CacheActivationsRunner). https://github.com/decoderesearch/SAELens/blob/main/docs/training_saes.md — accessed 2026-08-12. [SAE-pipeline, caching]
• Hugging Face — PyTorch training on Apple silicon. https://huggingface.co/docs/transformers/main/perf_train_special — accessed 2026-08-12. [MPS-limits]
• PyTorch — Apple Silicon Support (TorchServe docs). https://docs.pytorch.org/serve/hardware_support/apple_silicon_support.html — accessed 2026-08-12. [MPS]
• Apple — MLX Lazy Evaluation (docs). https://ml-explore.github.io/mlx/build/html/usage/lazy_evaluation.html — accessed 2026-08-12. [MLX-capture]
• Apple ML Research — Exploring LLMs with MLX and the Neural Accelerators in the M5 GPU (2025). https://machinelearning.apple.com/research/exploring-llms-mlx-m5 — accessed 2026-08-12. [Apple-Silicon]
• ml-explore — mlx-lm. https://github.com/ml-explore/mlx-lm — accessed 2026-08-12. [MLX]
• ggml-org — llama.cpp ; examples/eval-callback. https://github.com/ggml-org/llama.cpp ; https://github.com/ggml-org/llama.cpp/tree/master/examples/eval-callback — accessed 2026-08-12. [quantized-runtime-introspection]
• Apple — MTLCaptureManager (developer docs). https://developer.apple.com/documentation/metal/mtlcapturemanager — accessed 2026-08-12. [Metal-capture]
• vllm-metal — GPU Profiling docs. https://docs.vllm.ai/projects/vllm-metal/en/latest/profiling/ — accessed 2026-08-12. [Metal-profiling]
• alia-traces — Metal frame capture outside of Xcode (2020). https://alia-traces.github.io/metal/tools/xcode/2020/07/18/adding-framecapture-outside-of-xcode.html — accessed 2026-08-12. [Metal-capture]
• eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM (2025). https://arxiv.org/pdf/2508.10553 — accessed 2026-08-12. [remote-execution, 2025]
• Oakley (Eclectic Light) — APFS: How sparse files work (2024) ; Sparse files are common in APFS (2021). https://eclecticlight.co/2024/06/08/apfs-how-sparse-files-work/ ; https://eclecticlight.co/2021/03/29/sparse-files-are-common-in-apfs/ — accessed 2026-08-12. [APFS, disk-IO]
• Enabling Performant and Flexible Model-Internal Observability for LLM Inference (2026). https://arxiv.org/pdf/2605.11093 — accessed 2026-08-12. [systems-observability, 2026]

# §4.10 — Visualization and atlas prior art

• Nanda — Neuroscope. https://github.com/neelnanda-io/Neuroscope — accessed 2026-08-12. [atlas-prior-art]
• Lin / Decode Research — Neuronpedia. https://www.neuronpedia.org/ ; https://github.com/hijohnnylin/neuronpedia ; https://www.neuronpedia.org/blog/neuronpedia-is-now-open-source — accessed 2026-08-12. [atlas-prior-art, API]
• OpenAI — Microscope (2020). https://openai.com/index/microscope/ ; https://microscope.openai.com/models — accessed 2026-08-12. [vision-atlas]
• Carter, Armstrong, Schubert, Johnson, Olah — Activation Atlas (Distill, 2019). https://distill.pub/2019/activation-atlas/ — accessed 2026-08-12. [atlas-prior-art]
• Transluce — Monitor ; Scaling Automatic Neuron Description (2024). https://transluce.org/observability-interface ; https://transluce.org/neuron-descriptions ; https://github.com/TransluceAI/observatory ; https://neurons.transluce.org/ — accessed 2026-08-12. [observability, neuron-catalog]
• Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers (2025). https://arxiv.org/pdf/2501.17727 — accessed 2026-08-12. [auto-interp-reliability, 2025]
• Vig — BertViz (2019). https://github.com/jessevig/bertviz — accessed 2026-08-12. [attention-viz]
• Hoover, Strobelt, Gehrmann — exBERT (2019). https://github.com/bhoov/exbert ; https://arxiv.org/abs/1910.05276 — accessed 2026-08-12. [viz]
• Alammar — Ecco (2021). https://github.com/jalammar/ecco — accessed 2026-08-12. [viz]
• Geva et al. — LM-Debugger (2022). https://github.com/mega002/lm-debugger ; https://arxiv.org/abs/2204.12130 — accessed 2026-08-12. [viz, intervention-UI]
• Gebru et al. — Datasheets for Datasets (2018). https://arxiv.org/abs/1803.09010 — accessed 2026-08-12. [provenance]
• Mitchell et al. — Model Cards for Model Reporting (2018). https://arxiv.org/abs/1810.03993 — accessed 2026-08-12. [provenance]
• Horwitz, Kurer, Kahana, Amar, Hoshen — Charting and Navigating Hugging Face's Model Atlas (2025). https://arxiv.org/abs/2503.10633 ; https://openreview.net/forum?id=BzFMBNqg7R ; https://horwitz.ai/model-atlas — accessed 2026-08-12. [model-atlas-naming, novelty]