Paper Citation Record · LEDGER

Interpreting and Steering Protein Language Models through Sparse Autoencoders

As of 8 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 7 inbound Pith citation observations for arXiv:2502.09135.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.09135 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T22:36:43.486001Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T19:48:43.577775Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-03T20:18:55.719686Z

Reference resolution

15 of 15 outbound references displayed

verified exact0
verified fuzzy6
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0983a381-1bb3-436a-ab0b-7bdf9897f5aa · outbound

This paper cites Simulating 500 million years of evolution with a language model.

Interpreting and Steering Protein Language Models through Sparse Autoencoders Simulating 500 million years of evolution with a language model

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T22:36:43.981991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation be4ff223-01f9-4368-87c6-c57aad4f025b · outbound

This paper cites Sparse autoencoders match supervised features for model steering on the ioi task.

Interpreting and Steering Protein Language Models through Sparse Autoencoders Sparse autoencoders match supervised features for model steering on the ioi task

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T22:36:43.972834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3db5407a-b667-4ca1-8d23-80a5baacbe3a · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Interpreting and Steering Protein Language Models through Sparse Autoencoders The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T22:36:43.465736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20fbe1f6-17e6-4357-aeb7-0892b8ce9c52 · outbound

This paper cites A practical review of mecha- nistic interpretability for transformer-based language models.

Interpreting and Steering Protein Language Models through Sparse Autoencoders A practical review of mecha- nistic interpretability for transformer-based language models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T22:36:43.469278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9046f5a8-ce6c-4d4a-809b-38b5a5ef3ab9 · outbound

This paper cites Interplm: Discovering interpretable features in protein language mod- els via sparse autoencoders.

Interpreting and Steering Protein Language Models through Sparse Autoencoders Interplm: Discovering interpretable features in protein language mod- els via sparse autoencoders

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T22:36:43.963643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 61b39b0c-3454-4f43-ae6a-cddec32683a9 · outbound

This paper cites Unpacking sdxl turbo: Interpreting text-to-image models with sparse autoencoders.

Interpreting and Steering Protein Language Models through Sparse Autoencoders Unpacking sdxl turbo: Interpreting text-to-image models with sparse autoencoders

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T22:36:43.478055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc68a3fe-1e7c-4703-94c7-2ee592e596ff · outbound

This paper cites pub/2024/scaling-monosemanticity/ [Accessed: 2024].

Interpreting and Steering Protein Language Models through Sparse Autoencoders pub/2024/scaling-monosemanticity/ [Accessed: 2024]

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T22:36:43.954539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9d1d0145-ab97-4e8f-8c26-dc107eef772a · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Interpreting and Steering Protein Language Models through Sparse Autoencoders Scaling and evaluating sparse autoencoders

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-07T22:36:43.452236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 642a30c2-00b0-41fa-9fce-f5b6c9885a21 · outbound

This paper cites BERTology Meets Biology: Interpreting Attention in Protein Language Models.

Interpreting and Steering Protein Language Models through Sparse Autoencoders BERTology Meets Biology: Interpreting Attention in Protein Language Models

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T22:36:43.483055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e3bc80d-d4bc-408b-88ba-5b3cb32f1229 · outbound

This paper cites URL https://www.biorxiv.org/content/10.1101/622803v4.

Interpreting and Steering Protein Language Models through Sparse Autoencoders URL https://www.biorxiv.org/content/10.1101/622803v4

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T22:36:43.472347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23bb49e9-3011-40bf-94ad-990fc8283b5a · outbound

This paper cites dead” and we re-initialize its weights to “revive.

Interpreting and Steering Protein Language Models through Sparse Autoencoders dead” and we re-initialize its weights to “revive

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T22:36:43.945273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b5e17813-291d-4a4a-906c-8c97f5ce0504 · outbound

This paper cites Ahmed Elnaggar, Michael Heinzinger, Christian Dallago, Ghalia Rehawi, Yu Wang, Llion Jones, Tom Gibbs, Tamas Feher, Christoph Angerer, Martin Steinegger, et al.

Interpreting and Steering Protein Language Models through Sparse Autoencoders Ahmed Elnaggar, Michael Heinzinger, Christian Dallago, Ghalia Rehawi, Yu Wang, Llion Jones, Tom Gibbs, Tamas Feher, Christoph Angerer, Martin Steinegger, et al

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T22:36:43.991420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c4057a2c-3711-4658-9bc2-f6702e98a5ae · outbound

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

Interpreting and Steering Protein Language Models through Sparse Autoencoders Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T22:36:43.445060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2900484-feaa-4a76-9f6c-e81ae6ffbf6c · outbound

This paper cites The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision.

Interpreting and Steering Protein Language Models through Sparse Autoencoders The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T22:36:43.455838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ef76fbd-ef75-4f70-bb55-097006bf6939 · outbound

This paper cites URL https: //www.biorxiv.org/content/early/2025/02/08/2025.02.06.636901.

Interpreting and Steering Protein Language Models through Sparse Autoencoders URL https: //www.biorxiv.org/content/early/2025/02/08/2025.02.06.636901

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T22:36:43.440810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 30a9dd85-a2ad-4329-ad1c-520bda0b009f · inbound

FoldSAE: Learning to Steer Protein Folding Through Sparse Representations cites this paper.

FoldSAE: Learning to Steer Protein Folding Through Sparse Representations Interpreting and Steering Protein Language Models through Sparse Autoencoders

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T19:48:43.577775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8dffb56-7763-4b6c-b197-716ce2d85b30 · inbound

GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models cites this paper.

GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models Interpreting and Steering Protein Language Models through Sparse Autoencoders

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T11:06:05.083104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5688a3e6-800c-49b3-9291-55dbdb416c84 · inbound

Retrieval and competition: how a protein foundation model starts a protein cites this paper.

Retrieval and competition: how a protein foundation model starts a protein Interpreting and Steering Protein Language Models through Sparse Autoencoders

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-21T00:13:53.258067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6ba64090-3daa-422f-8aed-ee495ac61aa3 · inbound

Retrieval and competition: how a protein foundation model starts a protein cites this paper.

Retrieval and competition: how a protein foundation model starts a protein Interpreting and Steering Protein Language Models through Sparse Autoencoders

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-01T00:25:10.451487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation accd937e-220d-4116-acf0-9104311ee426 · inbound

Interpretable enzyme function prediction via sparse autoencoder features of ESMC across the microbial protein universe cites this paper.

Interpretable enzyme function prediction via sparse autoencoder features of ESMC across the microbial protein universe Interpreting and Steering Protein Language Models through Sparse Autoencoders

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-03T13:38:19.499806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 49c8763f-170b-44a8-867a-f6bea122b476 · inbound

PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding cites this paper.

PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding Interpreting and Steering Protein Language Models through Sparse Autoencoders

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T18:55:58.722006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 01f27d1a-37f0-4c0c-b199-5883b96b0d4d · inbound

Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders cites this paper.

Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders Interpreting and Steering Protein Language Models through Sparse Autoencoders

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-07-03T20:18:55.722074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.