Paper Citation Record · LEDGER

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability

As of 14 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 9 inbound Pith citation observations for arXiv:2507.02559.

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

pith.paper-citation-record.v1
2507.02559 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T20:31:18.269637Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:11:43.051506Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T17:35:51.305374Z

Reference resolution

40 of 40 outbound references displayed

verified exact0
verified fuzzy14
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c869a743-df52-4b73-b291-c0d95f896c6b · outbound

This paper cites an unresolved cited work.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:15.056089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0c8e58f-c08b-40df-acbc-810dffbea027 · outbound

This paper cites an unresolved cited work.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:15.172686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e041b568-94b6-450a-a69f-aece269aa919 · outbound

This paper cites Why do LLMs attend to the first token?.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Why do LLMs attend to the first token?

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:15.257797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11fdb6d2-f6eb-4844-bea2-6740f89faba2 · outbound

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

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Towards monosemanticity: Decomposing language models with dictionary learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:15.344778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dde8764f-8c93-4737-b02f-420c9baa97b3 · outbound

This paper cites The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:15.407102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42a3c983-8edd-4529-9f24-b064e7bff7fc · outbound

This paper cites A mathematical framework for transformer circuits.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability A mathematical framework for transformer circuits

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:15.553041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e68b7bf3-5b83-4e2e-bd7f-67b328e240c4 · outbound

This paper cites Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:15.674321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d20ea447-be10-4c78-90b7-ed412a0a938a · outbound

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

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:15.779455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 798e706f-9568-4c43-9375-68cdc5b1949b · outbound

This paper cites Finding alignments between interpretable causal variables and distributed neural representations.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Finding alignments between interpretable causal variables and distributed neural representations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:15.884759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e73c837d-6e25-471b-a3a7-fab05156562f · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Gemini: A Family of Highly Capable Multimodal Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:15.963355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb4e697c-81f2-4f85-a760-a354b24aa4d9 · outbound

This paper cites Openwebtext corpus.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Openwebtext corpus

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:16.060049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 111d19bb-32ae-4288-b298-63ef7fc93219 · outbound

This paper cites Geometric interpretation of layer normalization and a comparative analysis with rmsnorm, 2025.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Geometric interpretation of layer normalization and a comparative analysis with rmsnorm, 2025

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:21.767788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7239c004-3271-4d79-b952-90e028f687bd · outbound

This paper cites Universal neurons in gpt2 language models.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Universal neurons in gpt2 language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:21.597286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 99434904-f61f-4b34-a984-1539183175a3 · outbound

This paper cites You can remove gpt2's LayerNorm by fine-tuning.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability You can remove gpt2's LayerNorm by fine-tuning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:21.426689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fe9d0fef-a56e-4bdb-be57-c2ff16090900 · outbound

This paper cites How to use and interpret activation patching.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability How to use and interpret activation patching

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:16.371013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1b3b626-81be-4d72-90fb-0700bf0324e7 · outbound

This paper cites Batch normalization: Accelerating deep network training by reducing internal covariate shift.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Batch normalization: Accelerating deep network training by reducing internal covariate shift

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:21.086538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d04f406e-d069-4c5b-9e81-7b1851e40253 · outbound

This paper cites Visit: Visualizing and interpreting the semantic information flow of transformers.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Visit: Visualizing and interpreting the semantic information flow of transformers

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:20.802792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a35f9380-5228-4bcf-a980-eda9ca20e0e7 · outbound

This paper cites Sparse autoencoders work on attention layer outputs, Jan 2024.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Sparse autoencoders work on attention layer outputs, Jan 2024

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:20.597517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2c399d03-4f48-4f46-bda9-872795db513b · outbound

This paper cites an unresolved cited work.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:16.726988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 546eccdf-40c9-4f50-8908-d8228a2951a3 · outbound

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

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:16.822219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d07e6a75-ee99-41cb-86a3-0bb1d54231b9 · outbound

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

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Copy Suppression: Comprehensively Understanding an Attention Head

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:16.921232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3392b0e-1386-4c5d-8410-29acc96e6ab1 · outbound

This paper cites Locating and Editing Factual Associations in GPT.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Locating and Editing Factual Associations in GPT

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:17.012912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9be48507-3147-49c3-8d30-9f26f23fa5fe · outbound

This paper cites Tinymodel: A tinystories lm with saes and transcoders, 2024.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Tinymodel: A tinystories lm with saes and transcoders, 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:20.467692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation aa89992e-cd0f-4ba6-8fe5-32689f46f113 · outbound

This paper cites Attribution patching: Activation patching at industrial scale, Mar 2023 a.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Attribution patching: Activation patching at industrial scale, Mar 2023 a

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:20.385237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4c84a2a1-d6f1-4065-82e7-f136d1c90939 · outbound

This paper cites Exploratory analysis demo (transformerlens).

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Exploratory analysis demo (transformerlens)

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:20.225301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1dd69c8d-38aa-4cca-8965-b2d0889424cd · outbound

This paper cites Transformerlens.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Transformerlens

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:17.293516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f971a940-3747-46ba-bae3-76ae16767369 · outbound

This paper cites interpreting gpt: the logit lens, Aug 2020.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability interpreting gpt: the logit lens, Aug 2020

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:20.082358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e749d544-cfd0-4e1b-9617-f80df5827e35 · outbound

This paper cites an unresolved cited work.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:17.418514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ddc0416-7fcc-431f-8e6a-17f5efd33b43 · outbound

This paper cites Direct and indirect effects.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Direct and indirect effects

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:19.538617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9a41a79c-d3f2-494b-bef6-e251be332513 · outbound

This paper cites Confidence Regulation Neurons in Language Models.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Confidence Regulation Neurons in Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:17.531668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1e544b0-9800-4f08-b4d3-7f091708f47a · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability LLaMA: Open and Efficient Foundation Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:17.573752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a14a053-66b1-48d6-9c44-fe69d155270f · outbound

This paper cites Attention is all you need.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Attention is all you need

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:17.639147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c55ad8d-8a26-4887-b6e2-0b7c0c681830 · outbound

This paper cites Understanding the failure of batch normalization for transformers in nlp.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Understanding the failure of batch normalization for transformers in nlp

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:19.058706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a1e61622-ebda-4274-882d-000351d125d4 · outbound

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

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:17.798498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51304b89-5000-4a5d-90fe-45a9839812db · outbound

This paper cites Re-examining layernorm.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Re-examining layernorm

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:18.869243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 36a28ddc-1ade-4255-aca7-410308e28a62 · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Efficient Streaming Language Models with Attention Sinks

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:17.953864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e012156-7341-48ac-9b01-fb96607b4c76 · outbound

This paper cites Interpreting the Repeated Token Phenomenon in Large Language Models.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Interpreting the Repeated Token Phenomenon in Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:18.044410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44f04f6d-ef34-414e-be54-aa848e4d1365 · outbound

This paper cites Root mean square layer normalization, 2019.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Root mean square layer normalization, 2019

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:18.138243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1634cc7-c2df-4015-bd8e-792616b6dc9b · outbound

This paper cites Towards Best Practices of Activation Patching in Language Models: Metrics and Methods.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:18.203317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9d3462e-56da-4ec7-8cf4-b8fc3231803d · outbound

This paper cites Transformers without normalization, 2025.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Transformers without normalization, 2025

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:31:18.679971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation c1b618d1-fb46-4671-98c7-5601df990771 · inbound

Key and Value Weights Are Probably All You Need: On the Necessity of the Query, Key, Value weight Triplet in Self-Attention Transformers cites this paper.

Key and Value Weights Are Probably All You Need: On the Necessity of the Query, Key, Value weight Triplet in Self-Attention Transformers Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T03:40:50.558061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 84b8c5e9-ed7f-4d58-a553-8e19648e3cd2 · inbound

Discovering Interpretable Algorithms by Decompiling Transformers to RASP cites this paper.

Discovering Interpretable Algorithms by Decompiling Transformers to RASP Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T03:11:43.051506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23ef7d84-e166-4f62-8de0-541ef57c2998 · inbound

Gated Normalization Removal and Scale Anchoring in Pre-Norm Transformers cites this paper.

Gated Normalization Removal and Scale Anchoring in Pre-Norm Transformers Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-21T14:20:13.540889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5ac88c08-06e6-441e-ba65-605d304cf889 · inbound

Selective Neuron Amplification in Transformer Language Models cites this paper.

Selective Neuron Amplification in Transformer Language Models Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:25:52.362679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 42cc7a73-a64c-458f-9f99-2e469bff0c8f · inbound

Selective Neuron Amplification in Transformer Language Models cites this paper.

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:16:25.133581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a0fa120d-8d23-4b81-b0b6-15533262c7e2 · inbound

Towards Verifiable Transformers: Solver-Checkable Circuit Explanations cites this paper.

Towards Verifiable Transformers: Solver-Checkable Circuit Explanations Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T15:05:48.064804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b342e9cf-cb1f-4e01-bfaa-8a2cddd8a182 · inbound

Towards Verifiable Transformers: Solver-Checkable Circuit Explanations cites this paper.

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T13:29:53.932972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a357d3c0-3e46-4594-874e-a9d86d4d0a92 · inbound

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models cites this paper.

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability

Reference 95

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T17:35:51.306825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7dc6d4e6-4bc0-4830-a4e2-274b3eaefe57 · inbound

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models cites this paper.

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T09:34:34.461654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.