BAGEL trains per-layer logistic-regression probes on CLIP-defined concepts and compares per-class concept probabilities with dataset-level concept frequencies, visualizing the alignment in a knowledge graph.
Sanity checks for saliency maps
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs
BAGEL trains per-layer logistic-regression probes on CLIP-defined concepts and compares per-class concept probabilities with dataset-level concept frequencies, visualizing the alignment in a knowledge graph.