Training, Reading, and Editing Legible Transformers | Paper Citation Record

Observation 407a81a1-175d-4292-b626-8331c42ee219 · outbound

This paper cites Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors.

Training, Reading, and Editing Legible Transformers Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3efa7add-bed7-471a-a6e2-890af8586706 · outbound

This paper cites Legible-by-Construction: Attention and End-to-End Transformers.

Training, Reading, and Editing Legible Transformers Legible-by-Construction: Attention and End-to-End Transformers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0795a145-1052-406f-a73c-92bcec24a197 · outbound

This paper cites 2020 , howpublished =.

Training, Reading, and Editing Legible Transformers 2020 , howpublished =

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d54e5677-3604-437d-a779-333ee0408b12 · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

Training, Reading, and Editing Legible Transformers Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb73016b-80c7-4a42-95b5-f7e45f54614f · outbound

This paper cites Proceedings of EMNLP 2021 , pages =.

Training, Reading, and Editing Legible Transformers Proceedings of EMNLP 2021 , pages =

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94349126-7577-4d42-9591-3f9871d8f2e5 · outbound

This paper cites Proceedings of EMNLP 2022 , pages =.

Training, Reading, and Editing Legible Transformers Proceedings of EMNLP 2022 , pages =

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 611cf1ab-12c0-4e9a-ae99-0e4542957cee · outbound

This paper cites Transformer Circuits Thread, Anthropic , year =.

Training, Reading, and Editing Legible Transformers Transformer Circuits Thread, Anthropic , year =

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ba31ec8-2728-45c9-a8e5-3155ccc95c27 · outbound

This paper cites Transformer Circuits Thread, Anthropic , year =.

Training, Reading, and Editing Legible Transformers Transformer Circuits Thread, Anthropic , year =

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aed10cbe-1c61-4278-8c2f-504de41a3a1b · outbound

This paper cites International Conference on Learning Representations (ICLR) , year =.

Training, Reading, and Editing Legible Transformers International Conference on Learning Representations (ICLR) , year =

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 856e969d-42d5-4640-b14c-500b0b3eeaa5 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year =.

Training, Reading, and Editing Legible Transformers International Conference on Learning Representations (ICLR) , year =

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20d7174e-4a15-4eaf-a9e8-ba3f971f339e · outbound

This paper cites Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism.

Training, Reading, and Editing Legible Transformers Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28cb850d-f3ba-4112-baba-7b7fe565eafe · outbound

This paper cites Proceedings of ACL 2023 , year =.

Training, Reading, and Editing Legible Transformers Proceedings of ACL 2023 , year =

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d224d2e-8134-488d-9286-28d874a3b811 · outbound

This paper cites Proceedings of CoNLL 2023 , year =.

Training, Reading, and Editing Legible Transformers Proceedings of CoNLL 2023 , year =

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c4e79a8-6117-46ad-80c9-b1e18e2687ae · outbound

This paper cites 2022 , note=.

Training, Reading, and Editing Legible Transformers 2022 , note=

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74dac33c-fa99-425d-ade7-e9391e795b99 · outbound

This paper cites International Conference on Machine Learning (ICML) , series=.

Training, Reading, and Editing Legible Transformers International Conference on Machine Learning (ICML) , series=

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35aee08f-62ff-4d98-8e81-8ba03f2d0b95 · outbound

This paper cites International Conference on Machine Learning (ICML) , series=.

Training, Reading, and Editing Legible Transformers International Conference on Machine Learning (ICML) , series=

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88f3d825-b31a-44da-bcd9-53f52c1ca65c · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year=.

Training, Reading, and Editing Legible Transformers Advances in Neural Information Processing Systems (NeurIPS) , year=

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a93328-99ad-429f-aefb-6c00704042e6 · outbound

This paper cites IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year=.

Training, Reading, and Editing Legible Transformers IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc6c05e-d4a3-4988-b8de-e84426466baa · outbound

This paper cites an unresolved cited work.

Training, Reading, and Editing Legible Transformers Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f405e51-ece9-4435-8fdb-894e2704dcde · outbound

This paper cites International Conference on Machine Learning (ICML) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Machine Learning (ICML) , year=

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 065b0572-09da-4da5-878d-5bfe9c93a1a5 · outbound

This paper cites International Conference on Machine Learning (ICML) , series=.

Training, Reading, and Editing Legible Transformers International Conference on Machine Learning (ICML) , series=

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a73b26f-d8c0-4e1f-ad58-1f6c776e527d · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year=.

Training, Reading, and Editing Legible Transformers Advances in Neural Information Processing Systems (NeurIPS) , year=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e344fe8-ba09-45d5-bc22-1026796415eb · outbound

This paper cites Transformer Circuits Thread , year=.

Training, Reading, and Editing Legible Transformers Transformer Circuits Thread , year=

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57f78508-0a32-4aa6-a39d-dccad19456f9 · outbound

This paper cites Transformer Circuits Thread , year=.

Training, Reading, and Editing Legible Transformers Transformer Circuits Thread , year=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74b11013-f21c-4666-8196-814b120a9787 · outbound

This paper cites Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning.

Training, Reading, and Editing Legible Transformers Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88346f44-cbea-46e8-98ca-f0af60dbadde · outbound

This paper cites an unresolved cited work.

Training, Reading, and Editing Legible Transformers Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c87f6837-dc22-44b3-a4b7-958df53e262c · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year=.

Training, Reading, and Editing Legible Transformers Advances in Neural Information Processing Systems (NeurIPS) , year=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 271fd7de-0975-4bdf-b41f-e820e49e6df6 · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

Training, Reading, and Editing Legible Transformers Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6532e12e-44b7-489d-aef3-bb3b2df2faf6 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Learning Representations (ICLR) , year=

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5632e69a-fca4-40c0-8765-5e9e0ecccbb5 · outbound

This paper cites Categorizing Variants of Goodhart's Law.

Training, Reading, and Editing Legible Transformers Categorizing Variants of Goodhart's Law

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 166e90a4-5772-4e49-9641-cc68fadf30bd · outbound

This paper cites Towards Faithfully Interpretable.

Training, Reading, and Editing Legible Transformers Towards Faithfully Interpretable

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e3b09f0-d7ab-43ba-ae61-813a404d7738 · outbound

This paper cites NSFL: A Post-Training Neuro-Symbolic Fuzzy Logic Framework for Boolean Operators in Neural Embeddings.

Training, Reading, and Editing Legible Transformers NSFL: A Post-Training Neuro-Symbolic Fuzzy Logic Framework for Boolean Operators in Neural Embeddings

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3036d5c9-3c43-4177-9968-05ea765d451b · outbound

This paper cites International Conference on Machine Learning (ICML) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Machine Learning (ICML) , year=

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d8a3d0e-57ff-4594-889e-f12fbff1977e · outbound

This paper cites Annual Meeting of the Association for Computational Linguistics (ACL) , year=.

Training, Reading, and Editing Legible Transformers Annual Meeting of the Association for Computational Linguistics (ACL) , year=

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90df8222-3ebe-4716-b820-2a2c22ce6ed9 · outbound

This paper cites Transformer Circuits Thread , year=.

Training, Reading, and Editing Legible Transformers Transformer Circuits Thread , year=

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6efa3b6-d35b-46e2-9b02-7d4ca7bebf3f · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year=.

Training, Reading, and Editing Legible Transformers Advances in Neural Information Processing Systems (NeurIPS) , year=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 888c7626-4b91-4bbd-85f8-6d701390a12a · outbound

This paper cites Mixture of A Million Experts.

Training, Reading, and Editing Legible Transformers Mixture of A Million Experts

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c1fdcb6-3f40-435c-85ad-b4ca51e68eb6 · outbound

This paper cites GLU Variants Improve Transformer.

Training, Reading, and Editing Legible Transformers GLU Variants Improve Transformer

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f307046-c018-4936-bdaf-d4109b216f43 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Learning Representations (ICLR) , year=

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89e3453c-29c7-420e-a602-ba03acfb1fdf · outbound

This paper cites International Conference on Learning Representations (ICLR) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Learning Representations (ICLR) , year=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 627129a6-aa4a-4437-ac7d-3abb4825dd49 · outbound

This paper cites arXiv preprint arXiv:2510.12269 , year=.

Training, Reading, and Editing Legible Transformers arXiv preprint arXiv:2510.12269 , year=

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e65547a0-cfad-4e3e-a18c-ceeb33ad870c · outbound

This paper cites Logical Neural Networks.

Training, Reading, and Editing Legible Transformers Logical Neural Networks

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fb17424-b7fa-45ee-b65a-b97995c033eb · outbound

This paper cites Artificial Intelligence , volume=.

Training, Reading, and Editing Legible Transformers Artificial Intelligence , volume=

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53850b0f-2131-4263-a790-8de01afdad3c · outbound

This paper cites Artificial Intelligence , volume=.

Training, Reading, and Editing Legible Transformers Artificial Intelligence , volume=

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8616fa0e-1280-4bfc-b179-734f1167a14e · outbound

This paper cites Neural Logic Networks for Interpretable Classification.

Training, Reading, and Editing Legible Transformers Neural Logic Networks for Interpretable Classification

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17e81ff6-6ceb-487b-b301-b327e570d369 · outbound

This paper cites KAN: Kolmogorov-Arnold Networks.

Training, Reading, and Editing Legible Transformers KAN: Kolmogorov-Arnold Networks

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0eb4bf0-5d32-42e9-b2b8-cc7c818ab214 · outbound

This paper cites Transformer Circuits Thread , year=.

Training, Reading, and Editing Legible Transformers Transformer Circuits Thread , year=

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fd71964-8a42-470a-8340-92c2e8bd7df8 · outbound

This paper cites Interpreting Neural Networks through the Polytope Lens.

Training, Reading, and Editing Legible Transformers Interpreting Neural Networks through the Polytope Lens

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e17c05c9-5fa9-4496-9837-6984388c8889 · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Training, Reading, and Editing Legible Transformers Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91bee30e-38e3-4af0-b86f-7d18d1bf9fa2 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Training, Reading, and Editing Legible Transformers Scaling and evaluating sparse autoencoders

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc083155-ce44-4fb4-96c9-43058c755153 · outbound

This paper cites Proceedings of BlackboxNLP , year=.

Training, Reading, and Editing Legible Transformers Proceedings of BlackboxNLP , year=

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c407f29f-12c6-4879-96da-7cba56f072b9 · outbound

This paper cites International Conference on Machine Learning (ICML) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Machine Learning (ICML) , year=

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4efe61df-09cb-4850-92ae-475912d75974 · outbound

This paper cites Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens.

Training, Reading, and Editing Legible Transformers Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f9cd5b0-6a26-4482-874e-895f1a4a35bb · outbound

This paper cites Decomposing The Dark Matter of Sparse Autoencoders.

Training, Reading, and Editing Legible Transformers Decomposing The Dark Matter of Sparse Autoencoders

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fa62143-c4a6-4e01-b16f-2f525b11630a · outbound

This paper cites Not All Language Model Features Are One-Dimensionally Linear.

Training, Reading, and Editing Legible Transformers Not All Language Model Features Are One-Dimensionally Linear

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10ff4820-ca7b-49b9-9e43-7b4509e6865e · outbound

This paper cites OpenAI Blog , year=.

Training, Reading, and Editing Legible Transformers OpenAI Blog , year=

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efef99e7-71ff-4fb6-996a-9d03482a5b05 · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year=.

Training, Reading, and Editing Legible Transformers Advances in Neural Information Processing Systems (NeurIPS) , year=

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32496847-15d3-4b50-8c2e-6f4545de5f77 · outbound

This paper cites arXiv preprint arXiv:2506.15538 , year=.

Training, Reading, and Editing Legible Transformers arXiv preprint arXiv:2506.15538 , year=

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6cb9511-ab47-4020-be0c-38adefadde2f · outbound

This paper cites Automatically Interpreting Millions of Features in Large Language Models.

Training, Reading, and Editing Legible Transformers Automatically Interpreting Millions of Features in Large Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d00d4d54-7bdb-4701-8459-9922c8254e89 · outbound

This paper cites Annual Meeting of the Association for Computational Linguistics (ACL) , year=.

Training, Reading, and Editing Legible Transformers Annual Meeting of the Association for Computational Linguistics (ACL) , year=

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9b2859f-91da-4a34-961f-045678989d81 · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year=.

Training, Reading, and Editing Legible Transformers Advances in Neural Information Processing Systems (NeurIPS) , year=

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c8602a9-1f72-4caf-8d83-a308b9d42268 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Learning Representations (ICLR) , year=

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83fb9654-997a-48ce-90c7-cf0ef1d8c3eb · outbound

This paper cites Steering Language Models With Activation Engineering.

Training, Reading, and Editing Legible Transformers Steering Language Models With Activation Engineering

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a0a71ec-9625-4ec3-a1f4-4ca98bbae227 · outbound

This paper cites Annual Meeting of the Association for Computational Linguistics (ACL) , year=.

Training, Reading, and Editing Legible Transformers Annual Meeting of the Association for Computational Linguistics (ACL) , year=

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7546d70-935a-4faa-a2f7-c4e499d916eb · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Training, Reading, and Editing Legible Transformers Representation Engineering: A Top-Down Approach to AI Transparency

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a83829c6-57de-42a0-86cc-cef354efeeb4 · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year=.

Training, Reading, and Editing Legible Transformers Advances in Neural Information Processing Systems (NeurIPS) , year=

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 987e8bae-06e7-4bc0-946c-132d54f75858 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Learning Representations (ICLR) , year=

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0786268c-e492-4d02-9a6b-12ea1b3921b7 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Learning Representations (ICLR) , year=

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c2390da-5407-44c1-bacd-598d04e75195 · outbound

This paper cites Findings of EMNLP , year=.

Training, Reading, and Editing Legible Transformers Findings of EMNLP , year=

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c179f08a-bf55-4043-a07b-8f329e90768a · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year=.

Training, Reading, and Editing Legible Transformers Advances in Neural Information Processing Systems (NeurIPS) , year=

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8c77014-478d-4795-9af8-95c4f8da1177 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Learning Representations (ICLR) , year=

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdf8ee9f-987e-4f3f-ac4d-087c2190a571 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Learning Representations (ICLR) , year=

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ffe02d2-9325-4caf-a9bd-8dd602e44bd0 · outbound

This paper cites arXiv preprint arXiv:2510.03659 , year=.

Training, Reading, and Editing Legible Transformers arXiv preprint arXiv:2510.03659 , year=

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f73b222-f65e-49ae-933c-f21df051a62e · outbound

This paper cites Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution.

Training, Reading, and Editing Legible Transformers Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea9ea9ff-b0cf-4efa-8272-7408b1bf382a · outbound

This paper cites an unresolved cited work.

Training, Reading, and Editing Legible Transformers Unresolved cited work

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 571ef5ab-191e-4252-bf41-30fb2bb4159a · outbound

This paper cites , journal=.

Training, Reading, and Editing Legible Transformers , journal=

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbcdb90c-5d3e-489d-9eb6-adf35846f41a · outbound

This paper cites 2023 , howpublished=.

Training, Reading, and Editing Legible Transformers 2023 , howpublished=

Reference 77

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f5abae7-92e6-4b60-93cb-4394829d39ca · outbound

This paper cites Mathematical Models of Computation in Superposition.

Training, Reading, and Editing Legible Transformers Mathematical Models of Computation in Superposition

Reference 78

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94c1b8ca-a92a-42da-aebc-7580db9829b1 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year=.

Training, Reading, and Editing Legible Transformers International Conference on Learning Representations (ICLR) , year=

Reference 79

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers