This work was done during one weekend by research workshop participants and does not represent the work of Apart Research.
Interpretability 2.0
Accepted at the 
Interpretability 2.0
 research sprint on 
May 10, 2023

Othello Mechint playground

This is a modification of the “Trafo Mech Int playground” project (by Stefan Heimersheim and Jonathan Ng) to work on Othello-GPT instead of LLM. Maybe available in streamlit but might crash at some point due to memory limitations. Also available in a github repository to run locally.

Victor Levoso Fernandez, Edoardo Pona ,Abhay Sheshadri, Kunvar
4th place
3rd place
2nd place
1st place
 by peer review