3 articles.
Interpretability · Part 5Interpretability
Swap one activation between two prompts to find where GPT-2 tracks names and recalls facts, and measure how corruption and metric choices change the answer.
Interpretability · Part 8Interpretability
From hand-found circuits to attribution patching, transcoders and attribution graphs, run with circuit-tracer on Gemma 2 2B and tested by intervention.
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.
