ITDA dictionaries, built greedily from poorly reconstructed activations and decomposed by matching pursuit, match some SAE reconstruction performance at 100x lower training cost and enable SOTA cross-model layer similarity via Jaccard overlap.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models
ITDA dictionaries, built greedily from poorly reconstructed activations and decomposed by matching pursuit, match some SAE reconstruction performance at 100x lower training cost and enable SOTA cross-model layer similarity via Jaccard overlap.