Pith. sign in

Paper Citation Record · LEDGER

On the transferability of Sparse Autoencoders for interpreting compressed models

As of 21 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 0 inbound Pith citation observations for arXiv:2507.15977.

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

pith.paper-citation-record.v1
2507.15977 v1

Coverage vector

measured 50 of 50 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:24:45.829437Z

measured 50 of 50 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+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

50 of 50 outbound references displayed

  • verified exact1
  • verified fuzzy10
  • unresolved38
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 760a9c56-ce75-4a93-adb7-54fe81436325 · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

On the transferability of Sparse Autoencoders for interpreting compressed models Refusal in Language Models Is Mediated by a Single Direction

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.682800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.682800Z digest=sha256:a0cdc94e1175e6f7b227a558d8b153daed7b99db0ba493b9214d1cd1c451126f

Observation a27462fd-9d0c-40ab-abda-158bbb4ee638 · outbound

This paper cites Batchtopk: A simple improvement for topk-saes, 2024a.

On the transferability of Sparse Autoencoders for interpreting compressed models Batchtopk: A simple improvement for topk-saes, 2024a

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T15:24:47.226222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.686589Z digest=sha256:d8d0f2352a695ad915919a5184049bc86d1e1773f5b78a98cbad3b25ab9dd51e

Observation ad631d17-2349-45c2-aa50-c29b83211139 · outbound

This paper cites Towards efficient post-training quantization of pre-trained language models.

On the transferability of Sparse Autoencoders for interpreting compressed models Towards efficient post-training quantization of pre-trained language models

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T15:24:47.079081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.689846Z digest=sha256:b24729b60d6ea07eb0872b3b5f5a6af3b7ff72b0f8b886f959d651cb4c5fe619

Observation 7528f4df-94ec-40c7-bdd2-06122632f7fc · outbound

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

On the transferability of Sparse Autoencoders for interpreting compressed models A is for absorption: Studying feature splitting and absorption in sparse autoencoders, 2024

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.693011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.693011Z digest=sha256:7548df71b134f8bf1d8343b80b3df19a7255d801dea6e4a0602d903e578b965b

Observation feb6303c-88b6-4118-9349-2903a1b408f9 · outbound

This paper cites Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification.

On the transferability of Sparse Autoencoders for interpreting compressed models Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification

Reference 5

Resolution
verified exact
local_arxiv, observed 2026-08-06T15:24:46.226405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.696009Z digest=sha256:748cf86cf44250df06a17ac0e788da4ba5d519786527cd51517c40015f13c646

Observation 7031dfe9-5c38-4702-a192-33b10aadb435 · outbound

This paper cites Towards automated circuit discovery for mechanistic interpretability.

On the transferability of Sparse Autoencoders for interpreting compressed models Towards automated circuit discovery for mechanistic interpretability

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.698989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.698989Z digest=sha256:030c8330a61d1b3615e3dec6d093359329c29d8a4771d2f7ba62842471f21e27

Observation 4bb05150-e979-44bb-9967-c25e033bd83f · outbound

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

On the transferability of Sparse Autoencoders for interpreting compressed models Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.701860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.701860Z digest=sha256:9a2220562f60c1032c57e0b9647b09c6d0b4e38836664c2330f0ff57bb9fabd5

Observation df359496-e975-4035-b053-f8afe9e7b69a · outbound

This paper cites Sparsegpt: Massive language models can be accurately pruned in one-shot.

On the transferability of Sparse Autoencoders for interpreting compressed models Sparsegpt: Massive language models can be accurately pruned in one-shot

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T15:24:46.971245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.704986Z digest=sha256:e59694032660d57719ca4d67fd49898b2fa16566b22128b3d455017a4af5490c

Observation 84963b34-f298-471a-b9dd-55da487127de · outbound

This paper cites SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot.

On the transferability of Sparse Autoencoders for interpreting compressed models SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.707652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.707652Z digest=sha256:48fb67b4fdbee58b3e351b7d71e9d4b9a031295b2e1b8815113ab09988007049

Observation cf74b71b-4c41-4189-8c0e-a78541647893 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

On the transferability of Sparse Autoencoders for interpreting compressed models The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.710903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.710903Z digest=sha256:92c5435c5c6bb86099e01d45b2e8b8f88ebac718063ba46bba9580a42dd9aefa

Observation 21c0515c-4299-4cdc-887a-c30028ecf0d7 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

On the transferability of Sparse Autoencoders for interpreting compressed models Scaling and evaluating sparse autoencoders

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.716773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.716773Z digest=sha256:10235d2797e6135ccf448ade0e42ba4e0cde3df71a779f1246af93e3acb0cf5a

Observation 6aa18751-5fea-4c60-97d7-3b37f0f98a44 · outbound

This paper cites Openwebtext corpus.

On the transferability of Sparse Autoencoders for interpreting compressed models Openwebtext corpus

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.720231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.720231Z digest=sha256:9acc08cceafc392a3d257194448ce699dea9d0bb7f77f5287dd19eb9a3d9190f

Observation 8d7856fb-37c0-42b9-9015-23e72fdc72bd · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

On the transferability of Sparse Autoencoders for interpreting compressed models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.723250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.723250Z digest=sha256:6b27ad77354e4640c29272dd9983bf01a49d3ce7c0ae6975ab455802d7e99f42

Observation f25a916e-e558-4824-8691-95b94162b92c · outbound

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

On the transferability of Sparse Autoencoders for interpreting compressed models Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.726080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.726080Z digest=sha256:a8509adf142d59f913bb4a853a1d50d285459d363573883f4f34ab9953ed857c

Observation 9fac792e-7112-4c1c-a65e-99e65578bf71 · outbound

This paper cites Learning both Weights and Connections for Efficient Neural Networks.

On the transferability of Sparse Autoencoders for interpreting compressed models Learning both Weights and Connections for Efficient Neural Networks

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.729099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.729099Z digest=sha256:f180eeeb5869cd45189c17f8202bfa076fc33eb1c1efdb9d24d3faa2e2de204d

Observation ba35d281-c19b-4dce-9d8a-243398d6c23c · outbound

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

On the transferability of Sparse Autoencoders for interpreting compressed models How does gpt-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T15:24:46.834494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.732046Z digest=sha256:7ea977b07e196b020b61a0b93076f9905e87c5ca2d0c20a2531416b8c3614632

Observation 3dab2165-8a15-405d-bcf5-f46909beadd2 · outbound

This paper cites Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression.

On the transferability of Sparse Autoencoders for interpreting compressed models Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.734894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.734894Z digest=sha256:b261730e9632d4249693e5ab66f23c86f43cd6ed68c17a2f88ef16a900cb758b

Observation 0a599cdc-a07d-4dad-adfb-c16f25508174 · outbound

This paper cites Language model compression with weighted low-rank factorization.

On the transferability of Sparse Autoencoders for interpreting compressed models Language model compression with weighted low-rank factorization

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.738275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.738275Z digest=sha256:8da360030efb11527d11f02b8d3deac5acc95ea11ef4d5bb526b67928be6bd4f

Observation 3d6b0d2d-e612-4aa8-9daa-30bbd357ac43 · outbound

This paper cites an unresolved cited work.

On the transferability of Sparse Autoencoders for interpreting compressed models Unresolved cited work

Reference 20

Resolution
unresolved
raw_fallback, observed 2026-08-06T15:24:46.773790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.741361Z digest=sha256:3e969ca2df148e8d136af0564523b35502123dbe73d81f4535e05b4181160543

Observation 4112d7ac-bf41-414e-88b3-355f5663fc65 · outbound

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

On the transferability of Sparse Autoencoders for interpreting compressed models SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.744009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.744009Z digest=sha256:a944d16a2ed8719eeab210ab0ad84eab392093a3052da95a254dedf273bc8f65

Observation d1b6264e-c550-4059-84da-d981351810e3 · outbound

This paper cites Saebench: A comprehensive benchmark for sparse autoencoders in language model interpretability, 2025 b.

On the transferability of Sparse Autoencoders for interpreting compressed models Saebench: A comprehensive benchmark for sparse autoencoders in language model interpretability, 2025 b

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T15:24:46.720151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.746867Z digest=sha256:5347fcf4640247983c90ad223e3226a680c3dbb286543f5e66a82fcda963d918

Observation b13a9366-5b20-4c26-9cd0-b59e55016998 · outbound

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

On the transferability of Sparse Autoencoders for interpreting compressed models Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.749482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.749482Z digest=sha256:99c566afb89bf86a936cf36d18ad177050b994baaf5e319ecde6f1228cecc71c

Observation 24dd1b20-a7a7-4d39-8967-9b1121bcd397 · outbound

This paper cites Taking features out of superposition with sparse autoencoders, 2022.

On the transferability of Sparse Autoencoders for interpreting compressed models Taking features out of superposition with sparse autoencoders, 2022

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T15:24:46.677367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.752337Z digest=sha256:78aa680ff53a814698ff5f8a6e5dca4d95617f1914e639da69489fc861283c6d

Observation ba8ef8f1-9b1d-48bd-96f6-4a8756cb9402 · outbound

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

On the transferability of Sparse Autoencoders for interpreting compressed models Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.755574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.755574Z digest=sha256:1f934af590f32b33809f88d4e7b8eb405ce91eb44156ac3635c611064b62d400

Observation c53f52fc-e83d-4806-b8a5-1fdd6bd37801 · outbound

This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.

On the transferability of Sparse Autoencoders for interpreting compressed models Awq: Activation-aware weight quantization for on-device llm compression and acceleration

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T15:24:46.568765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.758194Z digest=sha256:14803dde047d943db38b85258e9ce589787d7db2447c61b8722ddf18203cf352

Observation f2aa06c7-a29f-4bde-869b-0710e68d086c · outbound

This paper cites Llm-pruner: On the structural pruning of large language models.

On the transferability of Sparse Autoencoders for interpreting compressed models Llm-pruner: On the structural pruning of large language models

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.760991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.760991Z digest=sha256:005637c4eb6a3de22e8fe89898660a7e19cb2b688c63e9d07f5abba7c147f46f

Observation f3cb0488-bec5-465d-b1a9-f4b58168d4f2 · outbound

This paper cites Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control.

On the transferability of Sparse Autoencoders for interpreting compressed models Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.763674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.763674Z digest=sha256:e5ec55a4f07d7b241fb119d5c84f41cd5bd05b29c48ac38f8173c71378c0bd70

Observation edb2ad18-8efb-47ad-947d-b95b94839753 · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

On the transferability of Sparse Autoencoders for interpreting compressed models Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.766432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.766432Z digest=sha256:7199e1959b7f0999e49154397e48ea5fdbc94b2350be24e2c9f0d72ffa050517

Observation c1ad57ed-b05f-4e7c-9dbf-c3bf23fb9dc1 · outbound

This paper cites Transformerlens.

On the transferability of Sparse Autoencoders for interpreting compressed models Transformerlens

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T15:24:46.492606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.769242Z digest=sha256:9b1d625c4bb172d39bd68d94f14f49db1dcfbda068d9c30509f0c439f717bf50

Observation 737c8818-a4d5-49f2-adf8-d23dba927c0c · outbound

This paper cites Sparse Autoencoders Trained on the Same Data Learn Different Features.

On the transferability of Sparse Autoencoders for interpreting compressed models Sparse Autoencoders Trained on the Same Data Learn Different Features

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.771905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.771905Z digest=sha256:4d238483da734b00c10bc8c9c55e0c7141a13c23d55e734aa77920d7df0d95c2

Observation aca1dfab-4f75-4f84-bad7-05d9b79535cd · outbound

This paper cites Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking.

On the transferability of Sparse Autoencoders for interpreting compressed models Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.774976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.774976Z digest=sha256:27568266a3528a495351711aea53bf31ad22d91089513317fa1ea3099ed9d574

Observation 2b655242-f1fe-4d1f-9a5b-65c26e230021 · outbound

This paper cites Language models are unsupervised multitask learners.

On the transferability of Sparse Autoencoders for interpreting compressed models Language models are unsupervised multitask learners

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.777736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.777736Z digest=sha256:d0a55859ce2750d2e425d8c576b36b3d11c6b49dfdefff896739993dca678f2b

Observation cfc83c62-feb4-4434-bd63-0fcc8d33e498 · outbound

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

On the transferability of Sparse Autoencoders for interpreting compressed models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.780183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.780183Z digest=sha256:8ca930f70f4e9e9e10f27c291c5ba619d4a17167ec9a25ab63335e32529712cb

Observation b24e3611-12d8-4704-a2db-70d60ead3a6b · outbound

This paper cites Compressing Large Language Models using Low Rank and Low Precision Decomposition.

On the transferability of Sparse Autoencoders for interpreting compressed models Compressing Large Language Models using Low Rank and Low Precision Decomposition

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.783003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.783003Z digest=sha256:a3633ffa479f6503e375520263bb392c162cf868a1f2634eeeba614279f8335d

Observation 5985607c-2a0e-48ee-8ddc-694be0deb64b · outbound

This paper cites OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models.

On the transferability of Sparse Autoencoders for interpreting compressed models OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.785929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.785929Z digest=sha256:853f51746bceb934a9d41f1598f6196142ec15f3e9e2ce93f09457c684005eae

Observation a064a843-4564-47bf-9a1a-eb1fd18f6acc · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

On the transferability of Sparse Autoencoders for interpreting compressed models A Simple and Effective Pruning Approach for Large Language Models

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.788773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.788773Z digest=sha256:18a6c9b4dfa6060e8e05d14b1e8b35dd7c38e2ed7dc08f8ea354cb61d3e15dc6

Observation 306e8008-3ae3-42ab-b69f-3f43b8adca64 · outbound

This paper cites Jermyn A., Turner N., Anil C., Denison C., Lasenby R.

On the transferability of Sparse Autoencoders for interpreting compressed models Jermyn A., Turner N., Anil C., Denison C., Lasenby R

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T15:24:46.406734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.791735Z digest=sha256:01a6a9f5236e8e3748bc7aeca40d3c820daca75813cb97e70b2accd170f85e59

Observation fdf01d2c-50f2-4ebf-aefd-a89114b00c9e · outbound

This paper cites an unresolved cited work.

On the transferability of Sparse Autoencoders for interpreting compressed models Unresolved cited work

Reference 39

Resolution
unresolved
raw_fallback, observed 2026-08-06T15:24:46.378493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.794245Z digest=sha256:0a26f0bb478f9380412f6b9ae5699e9b1428de1a88d3bb54f2ddac77a66e70ee

Observation a3c62b1f-9dbd-4de9-8a60-06006bdf7583 · outbound

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

On the transferability of Sparse Autoencoders for interpreting compressed models Gemma 2: Improving Open Language Models at a Practical Size

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.796996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.796996Z digest=sha256:c13e511caf76b6b483008185a9f535d66d4f328c594b8bbe0a2880d146b82b33

Observation 368d6288-61c1-4521-831e-d739e5e9e78d · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

On the transferability of Sparse Autoencoders for interpreting compressed models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.800022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.800022Z digest=sha256:0cb5523cbc9c64df1bc6df063ac3cf91b34cf8f935c88d15a9e70a614ed1e269

Observation 81cc1615-1c03-46e6-9418-566592d76d4b · outbound

This paper cites Attention is all you need.

On the transferability of Sparse Autoencoders for interpreting compressed models Attention is all you need

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.802884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.802884Z digest=sha256:70b88620d7c4a9a798f292b455188989375b8e517c14553ecbd2df2b18e0834c

Observation 64e739de-8800-4a24-926d-73ab73659a3f · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

On the transferability of Sparse Autoencoders for interpreting compressed models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.806155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.806155Z digest=sha256:77299d82efca573371885d3de4255698bbcbb723834982a839f2092a3bcd8de3

Observation fdbd0438-a8ff-44be-b76b-3ea02b1d8bf1 · outbound

This paper cites High-Dimensional Data Analysis with Low-Dimensional Models: Principles, Computation, and Applications.

On the transferability of Sparse Autoencoders for interpreting compressed models High-Dimensional Data Analysis with Low-Dimensional Models: Principles, Computation, and Applications

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.809203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.809203Z digest=sha256:8e455c76324987920f65d00b57f51ffcee19460ae7a632a53cbbe1a16bae83be

Observation 65884f24-9200-4f34-bebf-8f9de9aec6c7 · outbound

This paper cites Smoothquant: Accurate and efficient post-training quantization for large language models.

On the transferability of Sparse Autoencoders for interpreting compressed models Smoothquant: Accurate and efficient post-training quantization for large language models

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T15:24:46.351574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-06T15:24:45.811884Z digest=sha256:acf95583b30c205465683fb703edcf79b1136bd7a3d2e795d49bcd73aefe129f

Observation 13ecddf7-a8ca-4638-9b6c-345b174940c9 · outbound

This paper cites Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression.

On the transferability of Sparse Autoencoders for interpreting compressed models Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.814486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.814486Z digest=sha256:2ac8a36aa8ef3b7c73bc3307c2daa2e83c8d7ea3e6cfce903e97d83f1e5903bf

Observation 06c2744e-c61d-4d7f-b0a9-a9d15332f48c · outbound

This paper cites A Survey on Efficient Inference for Large Language Models.

On the transferability of Sparse Autoencoders for interpreting compressed models A Survey on Efficient Inference for Large Language Models

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.817447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.817447Z digest=sha256:852c1c1993882102d2dfa5d7527b6772fe5e692eaf4860b356887181600fb4f8

Observation ab145ea5-c860-478e-91d4-28b2058d10b3 · outbound

This paper cites write newline.

On the transferability of Sparse Autoencoders for interpreting compressed models write newline

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.820211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.820211Z digest=sha256:912e3a51a44bd38160981f909d42759955d909eb7d1062a41d67866c9579bbe7

Observation 174a9b75-eda6-4048-83cf-1a80663bc16e · outbound

This paper cites @esa (Ref.

On the transferability of Sparse Autoencoders for interpreting compressed models @esa (Ref

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.823473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.823473Z digest=sha256:a5109b632f8c1e01d934af75d02efe29ab1eae8e7a6c77cba65ad2a81bc831f8

Observation e5d8699c-2438-4b27-b11f-466fc3647331 · outbound

This paper cites an unresolved cited work.

On the transferability of Sparse Autoencoders for interpreting compressed models Unresolved cited work

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-06T15:24:45.826414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.826414Z digest=sha256:faed9b41412d034c03161582d79fd8aa0c554e065e518fb568f426b70e7dd1a2

Observation 305392c5-c1e4-4b50-8d21-adaffd91a63f · outbound

This paper cites dzaL :3,cu' UW.

On the transferability of Sparse Autoencoders for interpreting compressed models dzaL :3,cu' UW

Reference 51

Resolution
malformed identifier
no resolver link, observed 2026-08-06T15:24:45.829437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:24:45.829437Z digest=sha256:f2493664e2f55505b0a3589a2b77a0cf3120b8b403bb1b2b9b4cbd25de8c6d49

Pith citing papers

No inbound Pith citation observations are available.