Ilyass Ouardi

Ilyass Ouardi

M.Sc. Computer Science Student at University of Milan. Researching mechanistic interpretability, representation geometry, and verifiable AI safety.

Reading List

Welcome to my reading library. Here you will find my reading lists split into two distinct subcategories: general non-academic books that broaden my perspective outside my studies, and a structured syllabus of foundational research papers in mechanistic interpretability and representation geometry.

📚 Books

A curated log of books I have read outside of my computer science coursework—spanning personal development, philosophy, spirituality, and classic literature—to explore new perspectives and take a break from the everyday rush.

🔬 Mechanistic Interpretability Papers

A structured, annotated syllabus of seminal papers in mechanistic interpretability, representation geometry, sparse autoencoders (SAEs), and causal model surgery, complete with key takeaways and critical notes for each work.