Skip to yearly menu bar Skip to main content


Poster

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

Luca Baroni ⋅ Galvin Khara ⋅ Joachim Schaeffer ⋅ Marat Subkhankulov ⋅ Stefan Heimersheim
2026 Poster

Abstract

Video

Chat is not available.