x

LESSWRONG

LW

Chatrik

Chatrik

Message

58

3y

Chatrik

58

3y

Chatrik — LessWrong

Characterizing stable regions in the residual stream of LLMs

by Jett Janiak, jacek, Chatrik, Giorgi Giglemiani, nlpet, and StefanHex

This research was completed for London AI Safety Research (LASR) Labs 2024. The team was supervised by @Stefan Heimershiem (Apollo Research). Find out more about the program and express interest in upcoming iterations here. This video is a short overview of the project presented on the final day of the...

Sep 26, 2024•43

Evaluating Synthetic Activations composed of SAE Latents in GPT-2

by Giorgi Giglemiani, nlpet, Chatrik, Jett Janiak, and StefanHex

This research was completed for London AI Safety Research (LASR) Labs 2024. The team was supervised by Stefan Heimershiem (Apollo Research). Find out more about the programme and express interest in upcoming iterations here. TL;DR We find that real activations cannot be mimicked using a “bag of SAE latents” with...

Sep 25, 2024•30