Paper Citation Record · LEDGER

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization

As of 15 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2608.13538.

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

pith.paper-citation-record.v1
2608.13538 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:41:55.529803Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

38 of 38 outbound references displayed

verified exact3
verified fuzzy13
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6e2699d7-d022-4a0c-9256-1567f0871051 · outbound

This paper cites Transformer Circuits Thread , note=.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Transformer Circuits Thread , note=

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:59.042370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1affec27-f2d8-4ffa-8886-f18b1f4584a3 · outbound

This paper cites an unresolved cited work.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:41:58.995996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 31efe1f0-cfcb-4432-b791-9c682c3e44ad · outbound

This paper cites an unresolved cited work.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:41:58.873358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fe654b2c-fd05-4cd5-8c53-063003ef5072 · outbound

This paper cites an unresolved cited work.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:41:58.784752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d10f1e15-9cc8-41c6-9ff3-5bc1c983db4d · outbound

This paper cites Daniel and Sumers, Theodore R.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Daniel and Sumers, Theodore R

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:58.716975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 76cdc4d1-e523-4d5a-92cb-1bcc510b49e9 · outbound

This paper cites 2025 , type =.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization 2025 , type =

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:58.648324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 476cb9b7-4c4d-48f9-962b-2a22011bb5fe · outbound

This paper cites Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:54.498329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5dcfbaf-a696-493b-97f1-ce8c3dd3259e · outbound

This paper cites 2023 , howpublished =.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization 2023 , howpublished =

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:54.531167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6320742b-d41c-416e-8efa-1b6bc5dbe3fd · outbound

This paper cites 2023 , url =.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization 2023 , url =

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:58.497535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4195e83d-ec77-4e8f-b3d8-7c9158a57434 · outbound

This paper cites Proceedings of the 42nd International Conference on Machine Learning , pages =.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Proceedings of the 42nd International Conference on Machine Learning , pages =

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:58.415077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 588180b6-85bd-47bd-a90e-7ba7e7ffcb39 · outbound

This paper cites SAGE : An Agentic Explainer Framework for Interpreting SAE Features in Language Models.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization SAGE : An Agentic Explainer Framework for Interpreting SAE Features in Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:54.646307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a9298e2-36de-45d9-adea-a808c1cdcd89 · outbound

This paper cites Enhancing Automated Interpretability with Output-Centric Feature Descriptions.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Enhancing Automated Interpretability with Output-Centric Feature Descriptions

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:54.664754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01c8ff22-c725-456e-8a1b-5e3031bed973 · outbound

This paper cites an unresolved cited work.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:41:58.320307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5ac950da-78f3-4999-a59a-66216a8c8d77 · outbound

This paper cites FADE : Why Bad Descriptions Happen to Good Features.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization FADE : Why Bad Descriptions Happen to Good Features

Reference 14

Resolution: verified exact; doi, observed 2026-08-14T04:41:56.224849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c760b2cc-4024-4c82-8aef-3cffbda132df · outbound

This paper cites Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-14T04:41:57.114752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d43e5a3f-9a00-40d9-a347-601dbbbf691a · outbound

This paper cites 2018 , editor =.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization 2018 , editor =

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:58.228237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 768b4613-b216-46da-901a-a87a4a4cb232 · outbound

This paper cites Unveiling L anguage- S pecific F eatures in L arge L anguage M odels via S parse A utoencoders.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Unveiling L anguage- S pecific F eatures in L arge L anguage M odels via S parse A utoencoders

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:54.810965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2eeceb1-1ba3-4953-9fda-5afef2b1cf1e · outbound

This paper cites L ingua L ens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization L ingua L ens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:54.845527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b83570eb-2eae-48dd-97b3-cd47d49aeeb1 · outbound

This paper cites Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering

Reference 19

Resolution: verified exact; doi, observed 2026-08-14T04:41:55.945074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d255b05a-e7cc-4558-a109-79af584feea0 · outbound

This paper cites Self-explaining.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Self-explaining

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:58.155199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2238c825-2094-43ce-95ac-c69dbd42d4c5 · outbound

This paper cites SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization

Reference 21

Resolution: metadata mismatch; local_arxiv, observed 2026-08-14T04:41:56.954831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3f6c9d8c-333c-4211-a6a5-9788c7e19745 · outbound

This paper cites 2024 , editor =.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization 2024 , editor =

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:58.047380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 39574116-ec61-47b0-b09d-b20d87a03b61 · outbound

This paper cites 2024 , editor =.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization 2024 , editor =

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:57.963348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4a4f8d2e-c8d3-4581-b4a5-fe8802221e59 · outbound

This paper cites Transformer Circuits Thread , year=.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Transformer Circuits Thread , year=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:55.054752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5092462b-565f-4b91-8cec-2d76fb38ec55 · outbound

This paper cites an unresolved cited work.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:41:57.832024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 569f25b6-c647-47f0-bead-2d38d5e60ca3 · outbound

This paper cites CoRR , volume =.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization CoRR , volume =

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:55.126001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 483cb5e1-4ead-4d12-a16e-c0d63c2cf6be · outbound

This paper cites Li and Zifan Carl Guo and Vincent Huang and Jacob Steinhardt and Jacob Andreas , year=.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Li and Zifan Carl Guo and Vincent Huang and Jacob Steinhardt and Jacob Andreas , year=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:55.174777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fb3e48c-4a56-42a0-a9c9-1cb9e7d8781f · outbound

This paper cites and Ameisen, Emmanuel and Chen, James and Kishylau, Dzmitry and Pearce, Adam and Tarng, Julius and Wu, Alex and Wu, Jeff and Zhang, Yang and Ziegler, Daniel M.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization and Ameisen, Emmanuel and Chen, James and Kishylau, Dzmitry and Pearce, Adam and Tarng, Julius and Wu, Alex and Wu, Jeff and Zhang, Yang and Ziegler, Daniel M

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:55.205025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b62a1a8-7413-4acc-8cb4-be4dda11dbcf · outbound

This paper cites 2025 , url=.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization 2025 , url=

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:57.715194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6950fd78-e937-44d4-9594-e8bb29e2a411 · outbound

This paper cites Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:55.264881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40d07c89-e7e8-4d27-b8c2-1cad1c56d298 · outbound

This paper cites Transferring.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Transferring

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:57.631585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1f0df701-05fd-44c8-80f0-bef1d7d961e0 · outbound

This paper cites Word Embeddings Are Steers for Language Models.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Word Embeddings Are Steers for Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:55.355133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0badedf2-48a6-4666-af8b-62f3fe087213 · outbound

This paper cites Multi-property Steering of Large Language Models with Dynamic Activation Composition.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Multi-property Steering of Large Language Models with Dynamic Activation Composition

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:55.381830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11649a84-4892-4c31-8d8b-9fa9d73ca408 · outbound

This paper cites an unresolved cited work.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:41:57.539429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6860f190-db55-4042-b9d6-27f1e10bdf22 · outbound

This paper cites Proceedings of the 29th Symposium on Operating Systems Principles , pages =.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Proceedings of the 29th Symposium on Operating Systems Principles , pages =

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:55.427984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a2a25fc-9faa-4dac-8447-e5f6830c4ac8 · outbound

This paper cites Advances in Neural Information Processing Systems , doi =.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Advances in Neural Information Processing Systems , doi =

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:57.432174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 028c7dd3-d9e7-49e5-af20-f43d3aafdf4c · outbound

This paper cites Transformers: State-of-the-Art Natural Language Processing.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Transformers: State-of-the-Art Natural Language Processing

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-14T04:41:55.502463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17c671e0-815d-43c9-9287-5e322ed73ae3 · outbound

This paper cites Learning.

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization Learning

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:41:57.274749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.