GPT-2 small solves indirect object identification via a circuit of 26 attention heads organized into seven functional classes discovered through causal interventions.
ArXiv , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
LOCA identifies an average of six minimal interpretable changes in intermediate representations that causally induce refusal on otherwise successful jailbreaks for Gemma and Llama models.
RAG is more effective and cost-efficient than fine-tuning for industrial QA adaptation on automotive datasets.
citing papers explorer
-
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
GPT-2 small solves indirect object identification via a circuit of 26 attention heads organized into seven functional classes discovered through causal interventions.
-
Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models
LOCA identifies an average of six minimal interpretable changes in intermediate representations that causally induce refusal on otherwise successful jailbreaks for Gemma and Llama models.
-
Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications
RAG is more effective and cost-efficient than fine-tuning for industrial QA adaptation on automotive datasets.