Cross-Layer Transcoders decompose ViT activations into sparse, depth-aware layer contributions that maintain zero-shot accuracy and enable faithful attribution of the final representation.
Interpreting clip with sparse linear concept embeddings (splice).Advances in Neural Information Processing Systems, 37:84298–84328
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision
Cross-Layer Transcoders decompose ViT activations into sparse, depth-aware layer contributions that maintain zero-shot accuracy and enable faithful attribution of the final representation.