A downloadable project

This report represents an informal investigation of an IOI circuit within the Mistral GPT2-Small x49 Battlestar transformer model, inspired by the work performed by Kevin Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris and Jacob Steinhardt  at Redwood Research in their Interpretability in the Wild paper and the mechanistic interpretability work conducted  by Neel Nanda.

Download

Download
Interpretability Hackathon Write up_Chris Mathwin.pdf 606 kB
Download
Battlestar_Investigation.ipynb 189 kB

Leave a comment

Log in with itch.io to leave a comment.