Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks Localised
Code models write Python when the prompt does not say which language to use. We ask a mechanistic question about that habit: is it produced by a small, findable group of components inside the model? We run one pipeline---mean ablation, activation patching, greedy circuit extraction, a random-control significance test,...
Harsh Kumar, T. Joshi, Rahul Maity et al.
· 0 citations