Where this topic leads

Topics that build on Truth Directions and Linear Probes

Once you have Truth Directions and Linear Probes, 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 (3)

Sparse Autoencoders for Interpretability: TopK, JumpReLU, Matryoshka, and Scaling
Residual Stream and Transformer Internals
Mechanistic Interpretability: Features, Circuits, and Causal Faithfulness

Core flagship topics (1)

Sparse Autoencoders for Interpretability: TopK, JumpReLU, Matryoshka, and Scalinglayer 4 · llm-construction