Hoagy Cunningham Finding Distributed Features In Llms With Sparse Autoencoders Tais 2024

Summary

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 ... Large language models are astonishingly capable and almost completely opaque. Inside every model sit billions of numbers that, ... In this talk, Joshua Engels discusses Slides: jinen.setpal.net/slides/sae.pdf. In this video, we explore how Vision Take your personal data back with Incogni! Use code WELCHLABS at the link below and get 60% off an annual plan: ... Notes: drive.google.com/file/d/1GTIqXS-vEiDz2rAPfdeB_5G5IjBfNkxF/view?usp=sharing. 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 ... Dubbing: [ English ] [ 한국어 ] In this video, we will look at a I made a video about one of my favorite papers! I hope you enjoy :) ===Summary=== "Applying 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, ... Dhanya Sridhar (IVADO + Université de Montréal + Mila) ...