spb/modelmap Public License

1---2project: modelmap3document: Phase 1 notes — §4.10 Visualization and atlas prior art4author: Simon-Pierre Boucher5contact: contact@spboucher.ai6website: https://modelmap.io7created: 2026-08-128status: draft9---1011# §4.10 — Visualization and atlas design1213## Prior atlases and browsers14- **Neuroscope** https://github.com/neelnanda-io/Neuroscope — max-activating examples for every MLP neuron in 25 small models. **The canonical suggestive-but-unfalsifiable atlas:** max-activating examples are actively misleading (Bolukbasi illusion); no controls, no uncertainty, no versioned provenance; unmaintained. Generation itself is cheap and Mac-feasible.15- **Neuronpedia** https://www.neuronpedia.org/ (open-sourced 2025: https://github.com/hijohnnylin/neuronpedia) — the field's central artifact host: 50M+ latents, 5+ TB, per-feature dashboards (activation histograms, logit effects, auto-interp scores), steering, attribution-graph hosting, full REST API. **The modelmap gap: no per-entry reproducibility contract** — no commit/config/hardware manifest that regenerates a dashboard, no confidence taxonomy; hosted data changes without versioned releases. A **local Neuronpedia instance is a plausible serving layer** for modelmap viewers rather than rebuilding dashboards.16- **OpenAI Microscope** (2020, vision) https://openai.com/index/microscope/ — exhaustive per-unit coverage + canonical "model organisms": both ideas modelmap inherits. No uncertainty/provenance.17- **Activation Atlases** (Distill 2019) https://distill.pub/2019/activation-atlas/ — the literal "atlas" ancestor; UMAP layouts are seed/hyperparameter-sensitive with no stability analysis — the beautiful-but-unfalsifiable failure mode charter §2 warns about. **Never done for LLMs with replication controls.**18- **Anthropic Scaling Monosemanticity interface** https://transformer-circuits.pub/2024/scaling-monosemanticity/ — activation spectra across strength deciles = an explicit **anti-cherry-picking device worth copying**; but features hand-picked, underlying model closed, artifact unversioned.19- **circuit-tracer + attribution-graph frontend** https://github.com/decoderesearch/circuit-tracer ; hosted graphs https://www.neuronpedia.org/graph/info ; library paper https://aclanthology.org/2025.blackboxnlp-1.14.pdf — **first mainstream browser with a built-in verification affordance** (feature interventions to test graph hypotheses). Limitations: graphs describe a replacement model; faithfulness bounded, not displayed per-edge; pruning thresholds shape what you see; no confidence levels or provenance manifests.20- **Transluce Monitor / neuron descriptions** https://transluce.org/observability-interface ; https://github.com/TransluceAI/observatory — LLM-generated descriptions of **all 458,752 neurons** of Llama-3.1-8B + live steer/ablate UI. Auto-interp descriptions unreliable (metrics can fail to distinguish trained from random transformers: https://arxiv.org/pdf/2501.17727); no causal-verification labels, no versioned provenance.21- **BertViz** https://github.com/jessevig/bertviz — most-used interp viz ever; attention ≠ explanation; a caution: **high adoption of a low-epistemics tool shaped years of over-claiming.**22- **exBERT** https://arxiv.org/abs/1910.05276 — early corpus-level aggregation (anecdote → statistics). **Ecco** https://github.com/jalammar/ecco — NMF factors without stability analysis. **LM-Debugger** https://arxiv.org/abs/2204.12130 — early observation+intervention coupling; single interpretive frame presented as ground truth.23- **Gemma Scope / Llama Scope** https://arxiv.org/abs/2408.05147 ; https://huggingface.co/google/gemma-scope ; https://arxiv.org/abs/2410.20526 — **best existing example of interpretability artifacts released with reproducible identity** (fixed weights, named hookpoints, versioned HF artifacts). Still: no per-feature confidence labels; seed-replication not surfaced. Running (not training) Gemma Scope SAEs on a 2B fits 16 GB — natural third-party input for modelmap cross-checks.2425## Provenance templates26- **Datasheets for Datasets** (Gebru et al. 2018) https://arxiv.org/abs/1803.09010 ; **Model Cards** (Mitchell et al. 2018) https://arxiv.org/abs/1810.03993 — direct templates for modelmap's **"map cards"**: commit hash, config, model hash+quantization, promptset checksums, hardware manifest, seeds, controls run, replication stats, confidence level. **No interpretability artifact host ships anything equivalent (verified across Neuronpedia, Neuroscope, Transluce, circuit-tracer).**2728## Uncertainty encoding — cross-cutting finding29Across all tools surveyed: **uncertainty is essentially never encoded visually.** Partial exceptions: Neuronpedia auto-interp scores (a scalar of simulation fit, not a CI, not causal validity); Anthropic activation-spectrum deciles (anti-cherry-picking, not uncertainty); circuit-tracer prunable thresholds (manipulable, not summarized). Nobody displays seed-replication rates, bootstrap CIs, or correlational-vs-causal status on the artifact. **The Level 0–3 badges have no prior art to copy — and none to compete with.**3031## Novelty check — "model atlas" naming collision32- Horwitz et al. 2025, *Charting and Navigating Hugging Face's Model Atlas*, https://arxiv.org/abs/2503.10633 ; https://horwitz.ai/model-atlas — maps the *inter-model* graph of HF (which checkpoint fine-tuned from which), **not model internals**. Name collision to record in novelty_check.md, not a scope overlap.33- **Verdict (2026-08-12): the project's bet is confirmed** — no existing atlas of LLM internals combines versioned entries + regeneration recipes + explicit confidence levels + published negative results. Closest partials: Gemma Scope (versioning without confidence), Neuronpedia (hosting/API without reproducibility contracts), circuit-tracer (verification affordance without provenance).3435## Design conclusions for modelmap.io361. Copy: exhaustive per-unit coverage (Microscope), activation-spectrum deciles (Anthropic), intervention affordances (circuit-tracer, LM-Debugger), corpus-level aggregation (exBERT).372. Avoid: max-activating-example-only views (Neuroscope), unstable DR layouts without stability analysis (Activation Atlases), auto-interp labels presented as ground truth (Transluce).383. Differentiate: map cards (datasheet-style provenance), visible Level 0–3 badges, seed-replication rates and ablation-scheme curves rendered on the artifact, negative-results section.394. Consider a local Neuronpedia instance as serving infrastructure; keep modelmap.io as the provenance-first publication layer.40