Multi-layer SAE transitions capture domain-specific signatures that distinguish OOD texts in Gemma-2 models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Domain Restriction via Multi SAE Layer Transitions
Multi-layer SAE transitions capture domain-specific signatures that distinguish OOD texts in Gemma-2 models.