Your Causal Variables Are Irreducibly Subjective

Mechanistic interpretability needs its own shoe leather era. Reproducing the labeling process will matter than reproducing the Github. Crossposted from Communication & Intelligence substack When we try to understand large language models, we like to invoke causality. And who can blame us? Causal inference comes with an impressive toolkit: directed acyclic graphs, potential outcomes, mediation analysis, formal identification results. It feels crisp. It feels reproducible. It feels like science.