SAE features in later DINOv2 layers align with ImageNet hierarchy, with two new metrics proposed to measure such alignment.
Generic attention- model explainability for interpreting bi-modal and encoder- decoder transformers
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.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders
SAE features in later DINOv2 layers align with ImageNet hierarchy, with two new metrics proposed to measure such alignment.