What Happened With Sparse Autoencoders

May 24, 2026

Media Summary: 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 ... 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 ...

What Happened With Sparse Autoencoders - Detailed Analysis & Overview

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 ... 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 ... In this video, we dive deep into the world of 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 ...

Bachelor of Science in Applied Physics Undergraduate Thesis Seminar on Monday, 14 June 2021, 11:00 AM (c) 2021. In this AI Research Roundup episode, Alex discusses the paper: 'Sanity Checks for In this AI Research Roundup episode, Alex discusses the paper: 'Understanding 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, ... Can AI-Generated Text Be Detected? Exploring Sparse Autoencoders!