49 citations · 122 across the 8 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
ObserverBench: Testing Mechanistic Estimates for Intervention and Control
Vijay Erramilli
Mechanistic interpretability is increasingly used to guide interventions such as activation steering, circuit removal, and safety monitoring. Yet an internal estimate that is accur…
cs.LG2026
Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability
Vijay Erramilli
Mechanistic interpretability seeks quantities that models do not expose directly: represented states, component effects, interactions, and responses to interventions. Patching, gra…