Credit: Avital Berry

Louis Jaburi

I lead research at Iliad. I work on data attribution, rigorous interpretability, and the theory of deep learning.

Previously, I worked in the interpretability team at EleutherAI and was a fellow at MATS. Before that, I completed my PhD at Imperial College London in 2024 under Ana Caraiani, working on arithmetic geometry, representation theory, and number theory.

News and Updates:

• 10/2026: Exploring the data landscape via metagradient descent, with Benjamin Shaffrey and Xavier Poncini.
• 05/2025: Just put out two parts on the philosophical foundation of mechanistic interpretability: I. Is mechinterp good? and II. What is good mechinterp?
• 02/2025: Check out our new blog post exploring complexity, (hierarchial) generalization, and its relationship with various empirical metrics.
• 10/2024: New paper on rigorous mechanistic interpretability on toy models.