Sign up to save your podcasts
Or
Share Alex Spies - Structured Representations in Maze-Solving Transformers
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Alex Spies - Structured Representations in Maze-Solving Transformers
In this discussion, Alex Spies will provide an overview of mechanistic interpretability tools and the approaches researchers employ to "reverse engineer" transformer models. He will then explain how his team used some of these techniques to uncover emergent structures in the models they trained and how these structures may facilitate a systematic understanding of internal search processes.
What guarantees can Mechanistic Interpretability provide for logic-based programs (if any)?
Alex is a PhD student at Imperial College London who is currently in Tokyo as a Research Fellow at the National Institute of Informatics (NII).
View all episodes
By Blaine Rogers - Van NguyenIn this discussion, Alex Spies will provide an overview of mechanistic interpretability tools and the approaches researchers employ to "reverse engineer" transformer models. He will then explain how his team used some of these techniques to uncover emergent structures in the models they trained and how these structures may facilitate a systematic understanding of internal search processes.
What guarantees can Mechanistic Interpretability provide for logic-based programs (if any)?
Alex is a PhD student at Imperial College London who is currently in Tokyo as a Research Fellow at the National Institute of Informatics (NII).