Paper Citation Record · LEDGER

Towards Atoms of Large Language Models

As of 8 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2509.20784.

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

pith.paper-citation-record.v1
2509.20784 v3

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T15:20:32.225118Z

measured 38 of 38 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 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 exact0
verified fuzzy0
unresolved38
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0452359f-0be3-4ff1-9f6d-f2358be225e2 · outbound

This paper cites GPT-4 Technical Report.

Towards Atoms of Large Language Models GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.109848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a1305f3-858e-45b5-996b-a1fd6c7a0a36 · outbound

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

Towards Atoms of Large Language Models Language models can explain neurons in language models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.113112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c068fbf-1946-4573-be3b-0fb6493a3ca0 · outbound

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

Towards Atoms of Large Language Models Towards monosemanticity: Decomposing language models with dictionary learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.116116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a93462fa-87a4-4458-b968-399dd64ce0fb · outbound

This paper cites Language models are few-shot learners.

Towards Atoms of Large Language Models Language models are few-shot learners

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.119499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a8ad517-1171-4701-8618-4be505441825 · outbound

This paper cites Learning Multi-Level Features with Matryoshka Sparse Autoencoders.

Towards Atoms of Large Language Models Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.122570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03ef157a-3f20-49d9-a1e1-9269d179e672 · outbound

This paper cites Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information.

Towards Atoms of Large Language Models Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.125753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39dd5bbd-da5f-4b5d-9f17-13ff2ea29192 · outbound

This paper cites Feature hedging: Correlated features break narrow sparse autoencoders.

Towards Atoms of Large Language Models Feature hedging: Correlated features break narrow sparse autoencoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.129134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 503c4995-2e93-49d5-937e-9b36ee987673 · outbound

This paper cites The Knowledge Microscope: Features as Better Analytical Lenses than Neurons.

Towards Atoms of Large Language Models The Knowledge Microscope: Features as Better Analytical Lenses than Neurons

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.132190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94de39c8-3f67-40e1-ab48-ce3e6c7d8fa9 · outbound

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

Towards Atoms of Large Language Models Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.135376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e0d1c14-d098-4fad-a74a-3c149dbe7dd5 · outbound

This paper cites Compressed sensing.

Towards Atoms of Large Language Models Compressed sensing

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.138275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d69c0c6-c4fb-4581-8c26-789b7f13c488 · outbound

This paper cites The llama 3 herd of models.

Towards Atoms of Large Language Models The llama 3 herd of models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.141109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0d31a77-3c28-4991-8143-90623591692d · outbound

This paper cites A mathematical framework for transformer circuits.

Towards Atoms of Large Language Models A mathematical framework for transformer circuits

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.147836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cbe8958-da46-41f4-bc88-cc7ab51dbc16 · outbound

This paper cites Toy Models of Superposition.

Towards Atoms of Large Language Models Toy Models of Superposition

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.150924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97455bb9-7e02-4faf-8851-0e158bf16bed · outbound

This paper cites Decomposing The Dark Matter of Sparse Autoencoders.

Towards Atoms of Large Language Models Decomposing The Dark Matter of Sparse Autoencoders

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.153769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cec40596-0877-418b-92f2-6a141598e684 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Towards Atoms of Large Language Models Scaling and evaluating sparse autoencoders

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.156732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5352a3b0-4bb0-49c6-ad7d-c2ee2b106b71 · outbound

This paper cites Transformer Feed-Forward Layers Are Key-Value Memories.

Towards Atoms of Large Language Models Transformer Feed-Forward Layers Are Key-Value Memories

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.159654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0a413f7-9c02-4123-bd2a-7837170e3caa · outbound

This paper cites Finding Neurons in a Haystack: Case Studies with Sparse Probing.

Towards Atoms of Large Language Models Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.162715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7debc33-1c98-417d-9279-3b3b7223897b · outbound

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

Towards Atoms of Large Language Models Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.165968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69312b53-c1f1-477a-ade8-6fb620a5647f · outbound

This paper cites A structural probe for finding syntax in word representations.

Towards Atoms of Large Language Models A structural probe for finding syntax in word representations

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.168939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e4a300f-8ce5-4e9f-953b-71a4f732f442 · outbound

This paper cites Knowledge in superposition: Unveiling the failures of lifelong knowledge editing for large language models.

Towards Atoms of Large Language Models Knowledge in superposition: Unveiling the failures of lifelong knowledge editing for large language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.171906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 889197ce-1165-4e6c-aa70-4a2b7dce9c1c · outbound

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

Towards Atoms of Large Language Models Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.174473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b69a1cf-5ee6-446d-a612-ad4ca2cd43f3 · outbound

This paper cites Locating and editing factual associations in gpt.

Towards Atoms of Large Language Models Locating and editing factual associations in gpt

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.177256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa8db5d3-17e2-430c-a5c2-6ca8a5913e43 · outbound

This paper cites Emergent Linear Representations in World Models of Self-Supervised Sequence Models.

Towards Atoms of Large Language Models Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.180384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a74ead5-0965-4378-bf18-479be89ff688 · outbound

This paper cites Feature visualization.

Towards Atoms of Large Language Models Feature visualization

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.183586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b19a7e7b-83cc-4f46-887b-8adf80e7f271 · outbound

This paper cites Zoom in: An introduction to circuits.

Towards Atoms of Large Language Models Zoom in: An introduction to circuits

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.186304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60780d5f-74a1-4385-9266-7171d2fca26a · outbound

This paper cites Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders.

Towards Atoms of Large Language Models Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.189070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a417473-6d8a-484c-883c-d7e9f5247265 · outbound

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

Towards Atoms of Large Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.191948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8745fcc-a4d5-4722-84d1-8267c0386c53 · outbound

This paper cites Language Models as Knowledge Bases?.

Towards Atoms of Large Language Models Language Models as Knowledge Bases?

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.195035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 898753f7-4cfd-4a79-8692-d282a20413cb · outbound

This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.

Towards Atoms of Large Language Models Improving Dictionary Learning with Gated Sparse Autoencoders

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.198042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71629dbf-e71a-4909-96da-3041d7b65bcb · outbound

This paper cites Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders.

Towards Atoms of Large Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.200772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05de22b5-8ce6-46d0-a199-c16846a2f783 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Towards Atoms of Large Language Models Gemma 2: Improving Open Language Models at a Practical Size

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.203692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d23c7774-2fa1-41e0-9859-fd7ed884958c · outbound

This paper cites Daniel Freeman, Theodore R.

Towards Atoms of Large Language Models Daniel Freeman, Theodore R

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.206677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e26416c-ad34-4e77-ac51-298421cedf01 · outbound

This paper cites Wikidata: a free collaborative knowledgebase.

Towards Atoms of Large Language Models Wikidata: a free collaborative knowledgebase

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.209485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55316153-570d-44e7-bb76-991fd45bbdf4 · outbound

This paper cites Addressing feature suppression in saes.

Towards Atoms of Large Language Models Addressing feature suppression in saes

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.212154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bece62d-4711-4273-a677-b3f9b80e0942 · outbound

This paper cites write newline.

Towards Atoms of Large Language Models write newline

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.214850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58914705-1efc-4281-9d1f-46a0edb0dcf6 · outbound

This paper cites @esa (Ref.

Towards Atoms of Large Language Models @esa (Ref

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.218824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c244f1d-bde7-4cad-8b18-ed3e2de28507 · outbound

This paper cites an unresolved cited work.

Towards Atoms of Large Language Models Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.222020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb141a72-5288-4c09-bf01-00db7590293e · outbound

This paper cites an unresolved cited work.

Towards Atoms of Large Language Models Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.225118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.