Paper Citation Record · LEDGER

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition

As of 17 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 6 inbound Pith citation observations for arXiv:2504.20938.

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

pith.paper-citation-record.v1
2504.20938 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:21:34.095808Z

measured 57 of 57 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T10:40:01.662137Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

51 of 51 outbound references displayed

verified exact0
verified fuzzy21
unresolved29
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 841b2460-9333-4104-bae8-db0db3b94347 · outbound

This paper cites An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.854161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceae6dea-c0d5-4251-a414-04ee162b4c3d · outbound

This paper cites GQA: training generalized multi-query transformer models from multi-head checkpoints.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition GQA: training generalized multi-query transformer models from multi-head checkpoints

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.859560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df625bae-2760-4f66-8a81-9a207731c4b6 · outbound

This paper cites Investigating successor heads.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Investigating successor heads

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.769922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9b3906e0-73a7-4a95-a1a5-bca9a937d9ed · outbound

This paper cites an unresolved cited work.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.869155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 203a3c23-04fc-456c-b8b8-4930711d7017 · outbound

This paper cites Linear algebraic structure of word senses, with applications to polysemy.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Linear algebraic structure of word senses, with applications to polysemy

Reference 5

Resolution: malformed identifier; no resolver link, observed 2026-08-16T05:21:33.873953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81df82d4-9c4e-4d37-a38f-835d1e0ca6b7 · outbound

This paper cites Circuits updates - march 2024.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Circuits updates - march 2024

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.747690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 54b5c374-4026-4ff3-ba22-37e2805962d9 · outbound

This paper cites Pythia: A suite for analyzing large language models across training and scaling.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Pythia: A suite for analyzing large language models across training and scaling

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.883448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea670da-0da0-40e5-9a47-e225d88ec91e · outbound

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

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Language models can explain neurons in language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.888631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c046db1a-c4f2-429a-b961-8591ed0d48e0 · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Towards monosemanticity: Decomposing language models with dictionary learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.893071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e5a0caf-c503-46dc-84cb-59fb8b7be571 · outbound

This paper cites Learning multi-level features with matryoshka saes.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Learning multi-level features with matryoshka saes

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.706877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1dc1d14a-2357-4533-93e5-d22d75f7fd20 · outbound

This paper cites Circuits updates - february 2024.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Circuits updates - february 2024

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.692899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6eb2bb85-6b4b-4f0a-b88b-affe2090c58d · outbound

This paper cites Circuits updates - april 2024.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Circuits updates - april 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.678910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ae1b040f-4853-49ed-819a-e31cf022f2b3 · outbound

This paper cites Mavor - Parker, Aengus Lynch, Stefan Heimersheim, and Adri \` a Garriga - Alonso.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Mavor - Parker, Aengus Lynch, Stefan Heimersheim, and Adri \` a Garriga - Alonso

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.664772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 91d223b7-b1ee-4258-99fd-e118d10e9ef1 · outbound

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

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.917333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec24089e-a856-4782-9c6c-fce04bad0948 · outbound

This paper cites The Llama 3 Herd of Models.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition The Llama 3 Herd of Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.922838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5bf3096-13ae-4fc6-b63d-faf210e7058f · outbound

This paper cites Transcoders Find Interpretable LLM Feature Circuits.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Transcoders Find Interpretable LLM Feature Circuits

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.927686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc86a35e-f928-417a-a7c5-5ec4e77a78ca · outbound

This paper cites A mathematical framework for transformer circuits.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition A mathematical framework for transformer circuits

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.932861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebaf0d76-001b-4397-bda0-f42e89141370 · outbound

This paper cites Toy models of superposition.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Toy models of superposition

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.641060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e16a0c9f-c04d-4537-902d-0ce1ef1cc6e7 · outbound

This paper cites Privileged bases in the transformer residual stream.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Privileged bases in the transformer residual stream

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.627598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d9265d54-85bc-4c3f-a5d8-568997fd9610 · outbound

This paper cites Decomposing The Dark Matter of Sparse Autoencoders.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Decomposing The Dark Matter of Sparse Autoencoders

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.946749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff1f572f-93e7-43a3-9510-45cec4ace6bd · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Scaling and evaluating sparse autoencoders

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.951798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6cf6feb-bd66-40f0-a75d-681ee4e6d83e · outbound

This paper cites Automatically Identifying Local and Global Circuits with Linear Computation Graphs.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Automatically Identifying Local and Global Circuits with Linear Computation Graphs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.956907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a58857c1-5ada-4196-8028-fde66498b802 · outbound

This paper cites Successor heads: Recurring, interpretable attention heads in the wild.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Successor heads: Recurring, interpretable attention heads in the wild

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.612730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0ab48272-ce68-4d3b-a8b8-b70b03f3d1db · outbound

This paper cites Finding neurons in a haystack: Case studies with sparse probing.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Finding neurons in a haystack: Case studies with sparse probing

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.596174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bd92c09d-e49c-4120-a465-a4e346d61189 · outbound

This paper cites How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.582097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 818b2bf1-2217-4704-8910-06b8fca051c0 · outbound

This paper cites Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.974837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1859745b-79bc-462e-a3b7-664f1a81a826 · outbound

This paper cites Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.979344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba8cdf98-03f3-4ef8-97ed-0e872d23090f · outbound

This paper cites Circuits updates - january 2024.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Circuits updates - january 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.568332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7f224a36-a82f-44e2-9f41-d3d1094094d8 · outbound

This paper cites Interpreting Attention Layer Outputs with Sparse Autoencoders.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Interpreting Attention Layer Outputs with Sparse Autoencoders

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:33.990706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3613b24-d840-4eb9-aaf2-c378690cef2d · outbound

This paper cites We inspected every head in gpt-2 small using saes so you don’t have to.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition We inspected every head in gpt-2 small using saes so you don’t have to

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.554227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 577fe07b-c46c-48ea-a8ea-f9494129aaaf · outbound

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

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.000670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aa8995e-6ccb-4ff6-b9e7-ab4964fc8759 · outbound

This paper cites Sparse crosscoders for cross-layer features and model diffing.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Sparse crosscoders for cross-layer features and model diffing

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.539644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a8c42e8e-1bde-46a3-b6c7-2b9908ec22f2 · outbound

This paper cites an unresolved cited work.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.010473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b85343e4-9dc7-4f1d-8b7e-606bd1ed413d · outbound

This paper cites Copy Suppression: Comprehensively Understanding an Attention Head.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Copy Suppression: Comprehensively Understanding an Attention Head

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.015126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97b2d602-dc0f-4d0b-995e-5da403c2a3b4 · outbound

This paper cites Locating and editing factual associations in GPT.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Locating and editing factual associations in GPT

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.019977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d997c440-e44b-4baf-a679-a3adc47c2fce · outbound

This paper cites Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.024650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af6c29e5-309f-40ac-9a61-3cb047bf91b2 · outbound

This paper cites interpreting gpt: the logit lens.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition interpreting gpt: the logit lens

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.507329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 98d853a8-1720-4094-842b-dc2fe2656133 · outbound

This paper cites Circuits updates - july 2024.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Circuits updates - july 2024

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.492898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 93f757ae-d6f1-4fc3-9727-99f21e847a42 · outbound

This paper cites Zoom in: An introduction to circuits.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Zoom in: An introduction to circuits

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.038983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00284d91-c70e-4c63-bf78-a999c48d104f · outbound

This paper cites In-context learning and induction heads.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition In-context learning and induction heads

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.478775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b248592b-186f-4cab-9fb0-9aa1d116428f · outbound

This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Improving Dictionary Learning with Gated Sparse Autoencoders

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.047569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79db3ea2-c12f-4cd1-a85b-fd8073caaf59 · outbound

This paper cites SlimPajama: A 627B token cleaned and deduplicated version of RedPajama.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition SlimPajama: A 627B token cleaned and deduplicated version of RedPajama

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.052412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 271d5937-0142-44a2-8d91-b17868e71768 · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.056864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b1f6174-bb1e-4d50-9305-1de5845481cc · outbound

This paper cites Circuits updates - january 2024.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Circuits updates - january 2024

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.454542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1e307001-eaf0-49bd-a53e-be0e8e2240ff · outbound

This paper cites Daniel Freeman, Theodore R.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Daniel Freeman, Theodore R

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.440784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 529f19ca-c0c0-4510-ab3e-8d572bbe242d · outbound

This paper cites Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.073745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c8aa047-1c47-4bb0-9e99-39589cd655a7 · outbound

This paper cites Interpretability in the wild: a circuit for indirect object identification in GPT-2 small.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Interpretability in the wild: a circuit for indirect object identification in GPT-2 small

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.078512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24d7cee7-9a87-435d-b255-491aeacf4fb5 · outbound

This paper cites Addressing feature suppression in saes.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Addressing feature suppression in saes

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.416558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 68f4bc23-0f97-4463-b84a-2221f2d7af7c · outbound

This paper cites Retrieval Head Mechanistically Explains Long-Context Factuality.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.087163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 209b7b98-1cc0-43a8-b31c-47ba5881e880 · outbound

This paper cites Efficient streaming language models with attention sinks.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Efficient streaming language models with attention sinks

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.091712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b9c9586-66af-459f-aa6d-ef156412683a · outbound

This paper cites Towards best practices of activation patching in language models: Metrics and methods.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Towards best practices of activation patching in language models: Metrics and methods

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:21:34.392843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation c39b9499-16e6-4950-b3df-ba9b0e5c3b20 · inbound

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping cites this paper.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T15:35:32.846244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b5ce9711-390c-4319-9681-f6ab24dbc286 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:59:28.658104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4d84dd86-ebbf-4ee0-b0c9-3a182183b521 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-15T04:59:45.258995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 328a9f07-b921-4320-8a41-b73b6a33b28c · inbound

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers cites this paper.

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T23:32:46.682964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d0531adb-c723-4a4c-aa41-e2b524fd2c5b · inbound

Targeted Recovery of Weight-Space Mechanisms From Neural Networks cites this paper.

Targeted Recovery of Weight-Space Mechanisms From Neural Networks Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T10:39:48.151675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9b28670-8a8f-4615-a2f0-4485e8e3997d · inbound

Targeted Recovery of Weight-Space Mechanisms From Neural Networks cites this paper.

Targeted Recovery of Weight-Space Mechanisms From Neural Networks Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition

Reference 160

Resolution: unresolved; no resolver link, observed 2026-08-02T10:40:01.662137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.