Paper Citation Record · LEDGER

Evaluating SAE interpretability without explanations

As of 23 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 3 inbound Pith citation observations for arXiv:2507.08473.

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

pith.paper-citation-record.v1
2507.08473 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:24:52.521413Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T05:02:51.383123Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T14:23:30.730711Z

Reference resolution

31 of 31 outbound references displayed

verified exact1
verified fuzzy8
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 82bcfe99-8fda-4053-8bbf-26f566d20464 · outbound

This paper cites From mechanistic interpretability to mechanistic biology: Training, evaluating, and interpreting sparse autoencoders on protein language models.

Evaluating SAE interpretability without explanations From mechanistic interpretability to mechanistic biology: Training, evaluating, and interpreting sparse autoencoders on protein language models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:24:54.605768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 219379b0-a2d0-4faa-8c54-bb64b5abba40 · outbound

This paper cites SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model.

Evaluating SAE interpretability without explanations SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:50.360187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47144a4c-fd38-4e8c-bbd6-d03a2966b4e6 · outbound

This paper cites Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs.

Evaluating SAE interpretability without explanations Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:50.455819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75c812de-2076-4659-abb1-1d33c44a1092 · outbound

This paper cites Language models can explain neurons in language models.

Evaluating SAE interpretability without explanations Language models can explain neurons in language models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:24:54.449384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fe227b72-ccfb-4d8a-b1a8-632bbd80d096 · outbound

This paper cites Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization.

Evaluating SAE interpretability without explanations Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T18:24:53.303384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2c147c9c-345d-4283-805f-31c9f9e3743e · outbound

This paper cites Reading tea leaves: How humans interpret topic models.

Evaluating SAE interpretability without explanations Reading tea leaves: How humans interpret topic models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:24:54.285149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 888b6e5f-4340-4154-8c1a-d9d24aa19d0d · outbound

This paper cites A is for absorption: Studying feature splitting and absorption in sparse autoencoders, 2024.

Evaluating SAE interpretability without explanations A is for absorption: Studying feature splitting and absorption in sparse autoencoders, 2024

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:50.780922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7895f8ae-cbde-4e41-95e7-80cf0be35e5e · outbound

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

Evaluating SAE interpretability without explanations Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:50.875009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebbef96f-72b4-48ec-9e9e-65f41f72db67 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Evaluating SAE interpretability without explanations Scaling and evaluating sparse autoencoders

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:50.966835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dc2bc81-ca36-432c-96f4-b889f65766a2 · outbound

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

Evaluating SAE interpretability without explanations The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.055259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bab99dc-d58a-4897-a207-f157f837be27 · outbound

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

Evaluating SAE interpretability without explanations Enhancing Automated Interpretability with Output-Centric Feature Descriptions

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.096631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a50bec3-c959-4b47-af7f-34a36a929314 · outbound

This paper cites SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability.

Evaluating SAE interpretability without explanations SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.180244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5588cd8-eccd-402a-b791-69b3cb6c5229 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Evaluating SAE interpretability without explanations Adam: A Method for Stochastic Optimization

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.252747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68df6f77-0ab7-4466-a265-7855fc030ba9 · outbound

This paper cites From superposition to sparse codes: interpretable representations in neural networks.

Evaluating SAE interpretability without explanations From superposition to sparse codes: interpretable representations in neural networks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.328290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d09bee25-b238-425f-8bf4-50775d0c9729 · outbound

This paper cites Concept Bottleneck Models.

Evaluating SAE interpretability without explanations Concept Bottleneck Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.398140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef608de2-630d-491a-9053-69b01248b126 · outbound

This paper cites Learning biologically relevant features in a pathology foundation model using sparse autoencoders.

Evaluating SAE interpretability without explanations Learning biologically relevant features in a pathology foundation model using sparse autoencoders

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.445003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e207ae10-aca5-4ae7-bb5b-b35637abd0ca · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Evaluating SAE interpretability without explanations Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.490925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b231f97-8fd4-4e64-9058-4e18fd2cdbb3 · outbound

This paper cites Compositional Explanations of Neurons.

Evaluating SAE interpretability without explanations Compositional Explanations of Neurons

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.541971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ed14f3c-06e1-4796-bc8f-70f81dda4c00 · outbound

This paper cites Partially Rewriting a Transformer in Natural Language.

Evaluating SAE interpretability without explanations Partially Rewriting a Transformer in Natural Language

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:24:52.843511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6e6b6711-37ba-499f-b663-95b831dca041 · outbound

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

Evaluating SAE interpretability without explanations Automatically Interpreting Millions of Features in Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.640958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3589bb0f-3603-42e3-84bd-8cb9977fac8b · outbound

This paper cites Spine: Sparse interpretable neural embeddings.

Evaluating SAE interpretability without explanations Spine: Sparse interpretable neural embeddings

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:24:54.129460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 84a75aa4-6d5a-488b-bd85-be1070abb129 · outbound

This paper cites Unpacking sdxl turbo: Interpreting text-to-image models with sparse autoencoders, 2024.

Evaluating SAE interpretability without explanations Unpacking sdxl turbo: Interpreting text-to-image models with sparse autoencoders, 2024

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.766290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d2964b7-504a-4f00-9221-c49c86348ed2 · outbound

This paper cites The Llama 3 Herd of Models.

Evaluating SAE interpretability without explanations The Llama 3 Herd of Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.825557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff64be5b-f0c7-45cc-b993-9effba4be3ac · outbound

This paper cites Daniel Freeman, Theodore R.

Evaluating SAE interpretability without explanations Daniel Freeman, Theodore R

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.875108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f58d450-f26b-4f00-aee0-e64a6954daaa · outbound

This paper cites A sample survey study of poly-semantic neurons in deep cnns.

Evaluating SAE interpretability without explanations A sample survey study of poly-semantic neurons in deep cnns

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:24:53.967022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 77f3b985-ad1f-4ff2-9c56-3416f7d9ea43 · outbound

This paper cites Zimmermann, Thomas Klein, and Wieland Brendel.

Evaluating SAE interpretability without explanations Zimmermann, Thomas Klein, and Wieland Brendel

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:24:53.785484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7ef9b489-0c24-4859-b11c-e56fc91e2ccb · outbound

This paper cites Zimmermann, David A.

Evaluating SAE interpretability without explanations Zimmermann, David A

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:24:53.637297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ec1804b5-e4cb-46a1-aa8d-5a021b37e7a7 · outbound

This paper cites write newline.

Evaluating SAE interpretability without explanations write newline

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:52.156647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ecc6952-4f52-4ded-887d-537c24addf7b · outbound

This paper cites @esa (Ref.

Evaluating SAE interpretability without explanations @esa (Ref

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:52.337302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a204113-4d62-495d-abd6-fb40878bf376 · outbound

This paper cites an unresolved cited work.

Evaluating SAE interpretability without explanations Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:52.445651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98bdf8fb-2816-4220-a654-ee8107b20c25 · outbound

This paper cites f.[RQ^ UWM9 =qNղl 8sj W s sn|x` Wy i G2 q N.

Evaluating SAE interpretability without explanations f.[RQ^ UWM9 =qNղl 8sj W s sn|x` Wy i G2 q N

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:24:53.488648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 383acfd1-95fc-479c-940c-8c7bdf830e13 · inbound

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

Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features Evaluating SAE interpretability without explanations

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:27:59.001783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6352d0cd-9034-4684-9b59-2d1dda2092a1 · inbound

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations Evaluating SAE interpretability without explanations

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-06-29T14:23:30.732398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a101d157-3758-431b-9819-edb9f7677b77 · inbound

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations Evaluating SAE interpretability without explanations

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T05:02:51.383123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.