# You can remove GPT2's LayerNorm by fine-tuning

arXiv: https://arxiv.org/abs/2409.13710 · HTML: https://mlsanity.com/paper/2409.13710/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge and representations inside LLMs, one of 13 directions in Mechanistic interpretability.
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 6 Sep 2024.

## Placed in

- Mechanistic interpretability / [Knowledge and representations inside LLMs](https://mlsanity.com/mechinterp/knowledge-and-representations-inside-llms/)

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias](https://mlsanity.com/paper/2004.12265/) (2020)
- [Copy Suppression: Comprehensively Understanding an Attention Head](https://mlsanity.com/paper/2310.04625/) (2023)
- [Confidence Regulation Neurons in Language Models](https://mlsanity.com/paper/2406.16254/) (2024)
- [A technical note on bilinear layers for interpretability](https://mlsanity.com/paper/2305.03452/) (2023)

## Built on by (most cited first, 11 of 11)

- [Transformers without Normalization](https://mlsanity.com/paper/2503.10622/) (2025)
- [Stronger Normalization-Free Transformers](https://mlsanity.com/paper/2512.10938/) (2025)
- [Low-Rank Adapting Models for Sparse Autoencoders](https://mlsanity.com/paper/2501.19406/) (2025)
- [Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability](https://mlsanity.com/paper/2507.02559/) (2025)
- [Learning in Compact Spaces with Approximately Normalized Transformer](https://mlsanity.com/paper/2505.22014/) (2025)
- [Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference](https://mlsanity.com/paper/2501.15754/) (2025)
- [Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel](https://mlsanity.com/paper/2601.10266/) (2026)
- [Key and Value Weights Are Probably All You Need: On the Necessity of the Query, Key, Value weight Triplet in Self-Attention Transformers](https://mlsanity.com/paper/2510.23912/) (2025)
- [SCALAR: Benchmarking SAE Interaction Sparsity in Toy LLMs](https://mlsanity.com/paper/2511.07572/) (2025)
- [Interactions Between Crosscoder Features: A Compact Proofs Perspective](https://mlsanity.com/paper/2606.09940/) (2026)
- [Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models](https://mlsanity.com/paper/2607.15893/) (2026)

## Abstract (arXiv)

The LayerNorm (LN) layer in GPT-style transformer models has long been a hindrance to mechanistic interpretability. LN is a crucial component required to stabilize the training of large language models, and LN or the similar RMSNorm have been used in practically all large language models based on the transformer architecture. The non-linear nature of the LN layers is a hindrance for mechanistic interpretability as it hinders interpretation of the residual stream, and makes it difficult to decompose the model into circuits. Some researchers have gone so far as to name "reasons interpretability researchers hate layer norm." In this paper we show that it is possible to remove the LN layers from a pre-trained GPT2-small model by fine-tuning on a fraction (500M tokens) of the training data. We demonstrate that this LN-free model achieves similar performance to the original model on the OpenWebText and ThePile datasets (-0.05 cross-entropy loss), and the Hellaswag benchmark (-0.5% accuracy). We provide our implementation at https://github.com/ApolloResearch/gpt2_noLN, and fine-tuned GPT2-small models at https://huggingface.co/apollo-research/gpt2_noLN. Our work not only provides a simplified model for mechanistic interpretability research, but also provides evidence that the LN layers, at inference time, do not play a crucial role in transformer models.