Lilly Tech Systems
Mechanistic Interpretability
Get into mechanistic interpretability research. Learn the goal (reverse-engineer neural networks), key results (induction heads, circuits, sparse autoencoders), and tools.
6
Lessons
📋
Frameworks
✅
Practitioner-Tested
100%
Free
Lessons in This Topic
Work through these 6 lessons in order, or jump to whichever is most relevant to your role.