Interp vs mech interp: you can explain models without hunting for mechanisms

voooooogel · x · 2026-09-06

A debate within the interpretability community: @voooooogel argues for calling the broader group just "interp" rather than "mech interp," since these approaches explain models without necessarily seeking internal mechanisms. Pushing back on the framing of mech interp as "curiosity driven" vs probes as purely pragmatic, the author contends that non-mechanistic interp can be just as curiosity driven—top-down rather than bottom-up—and that pragmatists reach for non-mech tools mainly because they currently work better.

Original post →

More from Research

Research channel →