4 articles.
Interpretability · Part 3Interpretability
Train one-matrix classifiers on GPT-2 small and Qwen2.5-0.5B to read part of speech and truth from every layer, then check whether the probe did the work.
Interpretability · Part 10Interpretability
Word counts, then word pairs, then induction heads in 300 steps: 49 snapshots of the From Scratch model show what forms when, and what set the timing.
Interpretability · Part 11Interpretability
What looking inside a model can and can't check about its honesty: lie and sycophancy probes, model diffing and real audits, measured on Gemma 2 2B.
Interpretability · Part 12Interpretability
The series in review: every part's headline result, a robustness audit of three of them, the field's sharpest critiques, and the problems still open.
