spb/wpai0001_uqo
Public
1% WP-AI-0001 — references whose identifier, title, authors and date were verified against the arXiv API on 2026-11-09.2% primaryClass is not verified field-by-field; venue information (NeurIPS/ICML/ICLR/JMLR) is NOT included unless verified separately.3% Do not add entries to this file without verification; unverified candidates go to references_unverified.md.45@misc{achara2026multi,6 title = {{Multi-Way Representation Alignment}},7 author = {Akshit Achara and Tatiana Gaintseva and Mateo Mahaut and Pritish Chakraborty and Viktor Stenby Johansson and Melih Barsbey and Emanuele Rodolà and Donato Crisostomi},8 year = {2026},9 month = {2},10 eprint = {2602.06205},11 archivePrefix= {arXiv},12 primaryClass = {cs.LG},13 url = {https://arxiv.org/abs/2602.06205},14 note = {arXiv:2602.06205; metadata verified via arXiv API on 2026-11-09}15}1617@misc{agarwal2026cross,18 title = {{Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study}},19 author = {Ayushi Agarwal},20 year = {2026},21 month = {5},22 eprint = {2608.05164},23 archivePrefix= {arXiv},24 primaryClass = {cs.LG},25 url = {https://arxiv.org/abs/2608.05164},26 note = {arXiv:2608.05164; metadata verified via arXiv API on 2026-11-09}27}2829@misc{ainsworth2022git,30 title = {{Git Re-Basin: Merging Models modulo Permutation Symmetries}},31 author = {Samuel K. Ainsworth and Jonathan Hayase and Siddhartha Srinivasa},32 year = {2022},33 month = {9},34 eprint = {2209.04836},35 archivePrefix= {arXiv},36 primaryClass = {cs.LG},37 url = {https://arxiv.org/abs/2209.04836},38 note = {arXiv:2209.04836; metadata verified via arXiv API on 2026-11-09}39}4041@misc{bansal2021revisiting,42 title = {{Revisiting Model Stitching to Compare Neural Representations}},43 author = {Yamini Bansal and Preetum Nakkiran and Boaz Barak},44 year = {2021},45 month = {6},46 eprint = {2106.07682},47 archivePrefix= {arXiv},48 primaryClass = {cs.LG},49 url = {https://arxiv.org/abs/2106.07682},50 note = {arXiv:2106.07682; metadata verified via arXiv API on 2026-11-09}51}5253@misc{chen2025transferring,54 title = {{Transferring Linear Features Across Language Models With Model Stitching}},55 author = {Alan Chen and Jack Merullo and Alessandro Stolfo and Ellie Pavlick},56 year = {2025},57 month = {6},58 eprint = {2506.06609},59 archivePrefix= {arXiv},60 primaryClass = {cs.LG},61 url = {https://arxiv.org/abs/2506.06609},62 note = {arXiv:2506.06609; metadata verified via arXiv API on 2026-11-09}63}6465@misc{conmy2023towards,66 title = {{Towards Automated Circuit Discovery for Mechanistic Interpretability}},67 author = {Arthur Conmy and Augustine N. Mavor-Parker and Aengus Lynch and Stefan Heimersheim and Adrià Garriga-Alonso},68 year = {2023},69 month = {4},70 eprint = {2304.14997},71 archivePrefix= {arXiv},72 primaryClass = {cs.LG},73 url = {https://arxiv.org/abs/2304.14997},74 note = {arXiv:2304.14997; metadata verified via arXiv API on 2026-11-09}75}7677@misc{cristofano2026universal,78 title = {{Universal Refusal Circuits Across LLMs: Cross-Model Transfer via Trajectory Replay and Concept-Basis Reconstruction}},79 author = {Tony Cristofano},80 year = {2026},81 month = {1},82 eprint = {2601.16034},83 archivePrefix= {arXiv},84 primaryClass = {cs.LG},85 url = {https://arxiv.org/abs/2601.16034},86 note = {arXiv:2601.16034; metadata verified via arXiv API on 2026-11-09}87}8889@misc{cunningham2023sparse,90 title = {{Sparse Autoencoders Find Highly Interpretable Features in Language Models}},91 author = {Hoagy Cunningham and Aidan Ewart and Logan Riggs and Robert Huben and Lee Sharkey},92 year = {2023},93 month = {9},94 eprint = {2309.08600},95 archivePrefix= {arXiv},96 primaryClass = {cs.LG},97 url = {https://arxiv.org/abs/2309.08600},98 note = {arXiv:2309.08600; metadata verified via arXiv API on 2026-11-09}99}100101@misc{fan2026training,102 title = {{Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning}},103 author = {Jiahe Fan and Si Chen and Yinghao Hou and Aiyuan Zhang and Hong Xie},104 year = {2026},105 month = {7},106 eprint = {2608.13596},107 archivePrefix= {arXiv},108 primaryClass = {cs.LG},109 url = {https://arxiv.org/abs/2608.13596},110 note = {arXiv:2608.13596; metadata verified via arXiv API on 2026-11-09}111}112113@misc{geiger2023causal,114 title = {{Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability}},115 author = {Atticus Geiger and Duligur Ibeling and Amir Zur and Maheep Chaudhary and Sonakshi Chauhan and Jing Huang and Aryaman Arora and Zhengxuan Wu and Noah Goodman and Christopher Potts and Thomas Icard},116 year = {2023},117 month = {1},118 eprint = {2301.04709},119 archivePrefix= {arXiv},120 primaryClass = {cs.LG},121 url = {https://arxiv.org/abs/2301.04709},122 note = {arXiv:2301.04709; metadata verified via arXiv API on 2026-11-09}123}124125@misc{geiger2023finding,126 title = {{Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations}},127 author = {Atticus Geiger and Zhengxuan Wu and Christopher Potts and Thomas Icard and Noah D. Goodman},128 year = {2023},129 month = {3},130 eprint = {2303.02536},131 archivePrefix= {arXiv},132 primaryClass = {cs.LG},133 url = {https://arxiv.org/abs/2303.02536},134 note = {arXiv:2303.02536; metadata verified via arXiv API on 2026-11-09}135}136137@misc{gu2025beyond,138 title = {{Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Language Models through Latent Semantic Alignment}},139 author = {Jian Gu and Aldeida Aleti and Chunyang Chen and Hongyu Zhang},140 year = {2025},141 month = {10},142 eprint = {2510.24208},143 archivePrefix= {arXiv},144 primaryClass = {cs.LG},145 url = {https://arxiv.org/abs/2510.24208},146 note = {arXiv:2510.24208; metadata verified via arXiv API on 2026-11-09}147}148149@misc{gurnee2023finding,150 title = {{Finding Neurons in a Haystack: Case Studies with Sparse Probing}},151 author = {Wes Gurnee and Neel Nanda and Matthew Pauly and Katherine Harvey and Dmitrii Troitskii and Dimitris Bertsimas},152 year = {2023},153 month = {5},154 eprint = {2305.01610},155 archivePrefix= {arXiv},156 primaryClass = {cs.LG},157 url = {https://arxiv.org/abs/2305.01610},158 note = {arXiv:2305.01610; metadata verified via arXiv API on 2026-11-09}159}160161@misc{hendel2023context,162 title = {{In-Context Learning Creates Task Vectors}},163 author = {Roee Hendel and Mor Geva and Amir Globerson},164 year = {2023},165 month = {10},166 eprint = {2310.15916},167 archivePrefix= {arXiv},168 primaryClass = {cs.LG},169 url = {https://arxiv.org/abs/2310.15916},170 note = {arXiv:2310.15916; metadata verified via arXiv API on 2026-11-09}171}172173@misc{hernandez2023linearity,174 title = {{Linearity of Relation Decoding in Transformer Language Models}},175 author = {Evan Hernandez and Arnab Sen Sharma and Tal Haklay and Kevin Meng and Martin Wattenberg and Jacob Andreas and Yonatan Belinkov and David Bau},176 year = {2023},177 month = {8},178 eprint = {2308.09124},179 archivePrefix= {arXiv},180 primaryClass = {cs.LG},181 url = {https://arxiv.org/abs/2308.09124},182 note = {arXiv:2308.09124; metadata verified via arXiv API on 2026-11-09}183}184185@misc{huh2024platonic,186 title = {{The Platonic Representation Hypothesis}},187 author = {Minyoung Huh and Brian Cheung and Tongzhou Wang and Phillip Isola},188 year = {2024},189 month = {5},190 eprint = {2405.07987},191 archivePrefix= {arXiv},192 primaryClass = {cs.LG},193 url = {https://arxiv.org/abs/2405.07987},194 note = {arXiv:2405.07987; metadata verified via arXiv API on 2026-11-09}195}196197@misc{ilharco2022editing,198 title = {{Editing Models with Task Arithmetic}},199 author = {Gabriel Ilharco and Marco Tulio Ribeiro and Mitchell Wortsman and Suchin Gururangan and Ludwig Schmidt and Hannaneh Hajishirzi and Ali Farhadi},200 year = {2022},201 month = {12},202 eprint = {2212.04089},203 archivePrefix= {arXiv},204 primaryClass = {cs.LG},205 url = {https://arxiv.org/abs/2212.04089},206 note = {arXiv:2212.04089; metadata verified via arXiv API on 2026-11-09}207}208209@misc{kim2026one,210 title = {{One Adapter Pair per Model: A Universal Activation Interface for Language Models}},211 author = {Su-Hyeon Kim and Jiwan Mun and Yo-Sub Han},212 year = {2026},213 month = {8},214 eprint = {2608.09521},215 archivePrefix= {arXiv},216 primaryClass = {cs.LG},217 url = {https://arxiv.org/abs/2608.09521},218 note = {arXiv:2608.09521; metadata verified via arXiv API on 2026-11-09}219}220221@misc{kornblith2019similarity,222 title = {{Similarity of Neural Network Representations Revisited}},223 author = {Simon Kornblith and Mohammad Norouzi and Honglak Lee and Geoffrey Hinton},224 year = {2019},225 month = {5},226 eprint = {1905.00414},227 archivePrefix= {arXiv},228 primaryClass = {cs.LG},229 url = {https://arxiv.org/abs/1905.00414},230 note = {arXiv:1905.00414; metadata verified via arXiv API on 2026-11-09}231}232233@misc{lan2024quantifying,234 title = {{Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders}},235 author = {Michael Lan and Philip Torr and Austin Meek and Ashkan Khakzar and David Krueger and Fazl Barez},236 year = {2024},237 month = {10},238 eprint = {2410.06981},239 archivePrefix= {arXiv},240 primaryClass = {cs.LG},241 url = {https://arxiv.org/abs/2410.06981},242 note = {arXiv:2410.06981; metadata verified via arXiv API on 2026-11-09}243}244245@misc{lee2025shared,246 title = {{Shared Global and Local Geometry of Language Model Embeddings}},247 author = {Andrew Lee and Melanie Weber and Fernanda Viégas and Martin Wattenberg},248 year = {2025},249 month = {3},250 eprint = {2503.21073},251 archivePrefix= {arXiv},252 primaryClass = {cs.LG},253 url = {https://arxiv.org/abs/2503.21073},254 note = {arXiv:2503.21073; metadata verified via arXiv API on 2026-11-09}255}256257@misc{li2023inference,258 title = {{Inference-Time Intervention: Eliciting Truthful Answers from a Language Model}},259 author = {Kenneth Li and Oam Patel and Fernanda Viégas and Hanspeter Pfister and Martin Wattenberg},260 year = {2023},261 month = {6},262 eprint = {2306.03341},263 archivePrefix= {arXiv},264 primaryClass = {cs.LG},265 url = {https://arxiv.org/abs/2306.03341},266 note = {arXiv:2306.03341; metadata verified via arXiv API on 2026-11-09}267}268269@misc{lo2024large,270 title = {{Large Language Models Relearn Removed Concepts}},271 author = {Michelle Lo and Shay B. Cohen and Fazl Barez},272 year = {2024},273 month = {1},274 eprint = {2401.01814},275 archivePrefix= {arXiv},276 primaryClass = {cs.LG},277 url = {https://arxiv.org/abs/2401.01814},278 note = {arXiv:2401.01814; metadata verified via arXiv API on 2026-11-09}279}280281@misc{meng2022locating,282 title = {{Locating and Editing Factual Associations in GPT}},283 author = {Kevin Meng and David Bau and Alex Andonian and Yonatan Belinkov},284 year = {2022},285 month = {2},286 eprint = {2202.05262},287 archivePrefix= {arXiv},288 primaryClass = {cs.LG},289 url = {https://arxiv.org/abs/2202.05262},290 note = {arXiv:2202.05262; metadata verified via arXiv API on 2026-11-09}291}292293@misc{minixhofer2024zero,294 title = {{Zero-Shot Tokenizer Transfer}},295 author = {Benjamin Minixhofer and Edoardo Maria Ponti and Ivan Vulić},296 year = {2024},297 month = {5},298 eprint = {2405.07883},299 archivePrefix= {arXiv},300 primaryClass = {cs.LG},301 url = {https://arxiv.org/abs/2405.07883},302 note = {arXiv:2405.07883; metadata verified via arXiv API on 2026-11-09}303}304305@misc{nasirisarvi2025sparc,306 title = {{SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability}},307 author = {Ali Nasiri-Sarvi and Hassan Rivaz and Mahdi S. Hosseini},308 year = {2025},309 month = {7},310 eprint = {2507.06265},311 archivePrefix= {arXiv},312 primaryClass = {cs.LG},313 url = {https://arxiv.org/abs/2507.06265},314 note = {arXiv:2507.06265; metadata verified via arXiv API on 2026-11-09}315}316317@misc{ognev2026sharedsae,318 title = {{SharedSAE: One Feature Dictionary Across Language Models}},319 author = {Daniil Ognev and Célian Vasson and Lijie Hu and Kentaro Inui and Benjamin Heinzerling},320 year = {2026},321 month = {9},322 eprint = {2609.04344},323 archivePrefix= {arXiv},324 primaryClass = {cs.LG},325 url = {https://arxiv.org/abs/2609.04344},326 note = {arXiv:2609.04344; metadata verified via arXiv API on 2026-11-09}327}328329@misc{panigrahi2023task,330 title = {{Task-Specific Skill Localization in Fine-tuned Language Models}},331 author = {Abhishek Panigrahi and Nikunj Saunshi and Haoyu Zhao and Sanjeev Arora},332 year = {2023},333 month = {2},334 eprint = {2302.06600},335 archivePrefix= {arXiv},336 primaryClass = {cs.LG},337 url = {https://arxiv.org/abs/2302.06600},338 note = {arXiv:2302.06600; metadata verified via arXiv API on 2026-11-09}339}340341@misc{raghu2017svcca,342 title = {{SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability}},343 author = {Maithra Raghu and Justin Gilmer and Jason Yosinski and Jascha Sohl-Dickstein},344 year = {2017},345 month = {6},346 eprint = {1706.05806},347 archivePrefix= {arXiv},348 primaryClass = {cs.LG},349 url = {https://arxiv.org/abs/1706.05806},350 note = {arXiv:1706.05806; metadata verified via arXiv API on 2026-11-09}351}352353@misc{sinii2025small,354 title = {{Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors}},355 author = {Viacheslav Sinii and Nikita Balagansky and Gleb Gerasimov and Daniil Laptev and Yaroslav Aksenov and Vadim Kurochkin and Alexey Gorbatovski and Boris Shaposhnikov and Daniil Gavrilov},356 year = {2025},357 month = {9},358 eprint = {2509.06608},359 archivePrefix= {arXiv},360 primaryClass = {cs.LG},361 url = {https://arxiv.org/abs/2509.06608},362 note = {arXiv:2509.06608; metadata verified via arXiv API on 2026-11-09}363}364365@misc{sun2024massive,366 title = {{Massive Activations in Large Language Models}},367 author = {Mingjie Sun and Xinlei Chen and J. Zico Kolter and Zhuang Liu},368 year = {2024},369 month = {2},370 eprint = {2402.17762},371 archivePrefix= {arXiv},372 primaryClass = {cs.LG},373 url = {https://arxiv.org/abs/2402.17762},374 note = {arXiv:2402.17762; metadata verified via arXiv API on 2026-11-09}375}376377@misc{thasarathan2025universal,378 title = {{Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment}},379 author = {Harrish Thasarathan and Julian Forsyth and Thomas Fel and Matthew Kowal and Konstantinos G. Derpanis},380 year = {2025},381 month = {2},382 eprint = {2502.03714},383 archivePrefix= {arXiv},384 primaryClass = {cs.LG},385 url = {https://arxiv.org/abs/2502.03714},386 note = {arXiv:2502.03714; metadata verified via arXiv API on 2026-11-09}387}388389@misc{todd2023function,390 title = {{Function Vectors in Large Language Models}},391 author = {Eric Todd and Millicent L. Li and Arnab Sen Sharma and Aaron Mueller and Byron C. Wallace and David Bau},392 year = {2023},393 month = {10},394 eprint = {2310.15213},395 archivePrefix= {arXiv},396 primaryClass = {cs.LG},397 url = {https://arxiv.org/abs/2310.15213},398 note = {arXiv:2310.15213; metadata verified via arXiv API on 2026-11-09}399}400401@misc{turner2023steering,402 title = {{Steering Language Models With Activation Engineering}},403 author = {Alexander Matt Turner and Lisa Thiergart and Gavin Leech and David Udell and Juan J. Vazquez and Ulisse Mini and Monte MacDiarmid},404 year = {2023},405 month = {8},406 eprint = {2308.10248},407 archivePrefix= {arXiv},408 primaryClass = {cs.LG},409 url = {https://arxiv.org/abs/2308.10248},410 note = {arXiv:2308.10248; metadata verified via arXiv API on 2026-11-09}411}412413@misc{vig2020causal,414 title = {{Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias}},415 author = {Jesse Vig and Sebastian Gehrmann and Yonatan Belinkov and Sharon Qian and Daniel Nevo and Simas Sakenis and Jason Huang and Yaron Singer and Stuart Shieber},416 year = {2020},417 month = {4},418 eprint = {2004.12265},419 archivePrefix= {arXiv},420 primaryClass = {cs.LG},421 url = {https://arxiv.org/abs/2004.12265},422 note = {arXiv:2004.12265; metadata verified via arXiv API on 2026-11-09}423}424425@misc{wang2022interpretability,426 title = {{Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small}},427 author = {Kevin Wang and Alexandre Variengien and Arthur Conmy and Buck Shlegeris and Jacob Steinhardt},428 year = {2022},429 month = {11},430 eprint = {2211.00593},431 archivePrefix= {arXiv},432 primaryClass = {cs.LG},433 url = {https://arxiv.org/abs/2211.00593},434 note = {arXiv:2211.00593; metadata verified via arXiv API on 2026-11-09}435}436437@misc{yadav2023ties,438 title = {{TIES-Merging: Resolving Interference When Merging Models}},439 author = {Prateek Yadav and Derek Tam and Leshem Choshen and Colin Raffel and Mohit Bansal},440 year = {2023},441 month = {6},442 eprint = {2306.01708},443 archivePrefix= {arXiv},444 primaryClass = {cs.LG},445 url = {https://arxiv.org/abs/2306.01708},446 note = {arXiv:2306.01708; metadata verified via arXiv API on 2026-11-09}447}448449@misc{zhang2026negative,450 title = {{A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting}},451 author = {Peiyan Zhang and Jason Xin},452 year = {2026},453 month = {6},454 eprint = {2606.03280},455 archivePrefix= {arXiv},456 primaryClass = {cs.LG},457 url = {https://arxiv.org/abs/2606.03280},458 note = {arXiv:2606.03280; metadata verified via arXiv API on 2026-11-09}459}460461@misc{zou2023representation,462 title = {{Representation Engineering: A Top-Down Approach to AI Transparency}},463 author = {Andy Zou and Long Phan and Sarah Chen and James Campbell and Phillip Guo and Richard Ren and Alexander Pan and Xuwang Yin and Mantas Mazeika and Ann-Kathrin Dombrowski and Shashwat Goel and Nathaniel Li and Michael J. Byun and Zifan Wang and Alex Mallen and Steven Basart and Sanmi Koyejo and Dawn Song and Matt Fredrikson and J. Zico Kolter and Dan Hendrycks},464 year = {2023},465 month = {10},466 eprint = {2310.01405},467 archivePrefix= {arXiv},468 primaryClass = {cs.LG},469 url = {https://arxiv.org/abs/2310.01405},470 note = {arXiv:2310.01405; metadata verified via arXiv API on 2026-11-09}471}472