The paper shows that single-layer LoRA fine-tuning on OOCR tasks approximates a constant steering vector, and directly trained steering vectors reproduce OOCR.
Chris olah's views on AGI safety
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Simple Mechanistic Explanations for Out-Of-Context Reasoning
The paper shows that single-layer LoRA fine-tuning on OOCR tasks approximates a constant steering vector, and directly trained steering vectors reproduce OOCR.