Where this topic leads
Topics that build on Residual Stream and Transformer Internals
Once you have Residual Stream and Transformer Internals, 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 (4)
Core flagship topics (2)
- Mechanistic Interpretability: Features, Circuits, and Causal Faithfulnesslayer 4 · ai-safety
- Sparse Autoencoders for Interpretability: TopK, JumpReLU, Matryoshka, and Scalinglayer 4 · llm-construction
Standard topics (2)
- Induction Headslayer 4 · llm-construction
- Truth Directions and Linear Probeslayer 4 · ai-safety