You can remove GPT2's LayerNorm by fine-tuning

6 September 2024

Stefan Heimersheim

Papers citing "You can remove GPT2's LayerNorm by fine-tuning"

2 / 2 papers shown

Title
Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference Go Kamoda Benjamin Heinzerling Tatsuro Inaba Keito Kudo Keisuke Sakaguchi Kentaro Inui MILM 38 2 0 27 Jan 2025
A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models Daking Rai Yilun Zhou Shi Feng Abulhair Saparov Ziyu Yao 85 22 0 02 Jul 2024