factual
Mechanistic interpretability enables causal manipulation of features
Mechanistic interpretability can decode features from a model's internal layers, such as grammatical number or relative-clause boundaries, and then causally manipulate them to confirm that changing the feature changes behavior as predicted.
factualpending
Speaker
Chandra SripadaEvidence Quote
“we can causally manipulate it to close the circle and make sure, yeah, when we change this feature, the model's behavior changes as predicted”
Created: 11/17/2026, 6:53:48 AM
Your notes
Loading notes...