Skip to content
Jakub Smékal

Jakub Smékal

Descriptive Alt Text

I am a Stanford PhD student working on AI. I am interested in developing methods to better understand how AI models think and how to enable them to solve more complex problems. In particular, I am excited about the parallels between deep learning and probabilistic cognitive modeling and how they can be utilized for interpretability and robustness.

Latest Posts

Starting in mechanistic interpretability


  • GitHub