Sparse Autoencoders Unlearn Knowledge in LLMs | A Paper-Based Walkthrough

Описание: I made a video about one of my favorite papers! I hope you enjoy :)

===Summary===
"Applying Sparse Autoencoders to Unlearn Knowledge in Language Models" investigates using SAEs—tools that peer into the inside of LLMs—to remove undesirable capabilities from language models. In this video, I walk through the motivation of this work, the methods used, and the interesting results the authors found.

I highly recommend you read it for yourself here: https://arxiv.org/pdf/2410.19278#page...

===My other videos on Sparse Autoencoders===
Matroshkya SAEs:    • Matryoshka (Nested) Sparse Autoencoders Ex...  
SAEs from the Ground Up:    • A Window  Into LLMs | Sparse Autoencoders ...  

===Video Chapters===
0:00 Intro
0:14 Context/Motivation
0:46 SAE Negative Clamping
1:01 Feature Identification
1:35 Experimental Setup
1:49 Single-Feature Steering
2:24 Multi-Feature Steering
3:29 Investigating RMU Hypothesis