Activation patching provides evidence about neural network circuits when the choice of metric is aligned with the hypothesis and common interpretation errors are avoided.
Causal scrubbing: A method for rigorously testing interpretability hypotheses
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
How to use and interpret activation patching
Activation patching provides evidence about neural network circuits when the choice of metric is aligned with the hypothesis and common interpretation errors are avoided.