Media Summary: This has been my favorite video so far to make! I think interpretability is so important both in terms of ensuring safe AI and also ... One of the core roadblocks to understanding the computation inside a transformer is the fact that individual neurons do not seem ... Warning: This is an ad-libbed talk, and I'm sure I got some facts wrong. This is a talk I gave to my MATS 9.0 training program on ...
24 Sparse Autoencoders - Detailed Analysis & Overview
This has been my favorite video so far to make! I think interpretability is so important both in terms of ensuring safe AI and also ... One of the core roadblocks to understanding the computation inside a transformer is the fact that individual neurons do not seem ... Warning: This is an ad-libbed talk, and I'm sure I got some facts wrong. This is a talk I gave to my MATS 9.0 training program on ... I made a video about one of my favorite papers! I hope you enjoy :) ===Summary=== "Applying A visual explanation of how transformers piece concepts together, told in the style of 3Blue1Brown. Introducing SAEs. What truly ... ... Electrical Communication Engineering Department , IIT Kharagpur Discussion Content :
I had a lot of fun making this video! Nested SAEs are quite a brilliant solution overcoming a lot of the limitations of regular SAEs, ... In this video, we dive deep into the world of
![Hoagy Cunningham — Finding distributed features in LLMs with sparse autoencoders [TAIS 2024]](https://i.ytimg.com/vi/HPLIl9ZOpUQ/mqdefault.jpg)
