Where this topic leads
Topics that build on Mechanistic Interpretability: Features, Circuits, and Causal Faithfulness
Once you have Mechanistic Interpretability: Features, Circuits, and Causal Faithfulness, these are the topics that cite it as a prerequisite. Pick by tier and the area you want to push into next.
Editor's suggested next (6)
Core flagship topics (1)
- Sparse Autoencoders for Interpretability: TopK, JumpReLU, Matryoshka, and Scalinglayer 4 · llm-construction
Standard topics (3)
- Feature Importance and Interpretabilitylayer 2 · methodology
- Induction Headslayer 4 · llm-construction
- Truth Directions and Linear Probeslayer 4 · ai-safety