Decoding GPT: Mathematical foundations of Interpretability and Alignment for Large Language Models
A course in the Applied Mathematics and Statistics department, taught in the Spring 2024, Spring 2025, and Spring 2026 semesters at the Colorado School of Mines.
Course Materials on Github: github.com/mines-opt-ml/decoding-gpt
Instructors: Michael Ivanitskiy, Samy Wu Fung, Daniel McKenzie
Office hours poll (please include mines email)