finding
active
finding:feature-attribution-gradient-based-correlates-0-8-with-ablation-effects-on-the-john-and-kobe-examplesFeature attribution (gradient-based) correlates 0.8 with ablation effects on the 'John' and 'Kobe' examples.
Validation of attribution as a fast proxy for causal importance.
Source paper
extracted_from(2024) ·
Neighborhood — ranked by edge-count
Claims (1)
claim
- Gradient-based attribution approximates ablation impact, enabling fast search for causally important features.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Some gradient-based attribution methods give attributions independent of model and data-generating processfinding0.796Adebayo et al. sanity checks.
- Narrow-range greater-than feature.
- Capabilities.
- Baseline method against which probe-based ranking is compared; more computationally expensive.
- Structure of the computational pathway.
- Used by APD; poor approximations of causal importance.
- Implicit modulation.
- Motivation.