Blog Post··8 min read
Logit Lens: How Predictions Form Layer by Layer
Applying the unembedding matrix at intermediate layers to watch how a transformer's prediction evolves — and what direct logit attribution tells us about which components matter.
Tag: interpretability
Blog Post··12 min read
Open Problems in Mechanistic Interpretability
Faithfulness vs. plausibility, scaling to frontier models, the composition problem, automated interpretability, and what it would take to actually understand a large language model.