Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs
Jacob Dunefsky, Arman Cohan
Steering vectors (SVs) have emerged as a promising approach for interpreting and controlling LLMs, but current methods typically require large contrastive datasets that are often i…
cs.LG2024
Transcoders Find Interpretable LLM Feature Circuits
Jacob Dunefsky, Philippe Chlenski, Neel Nanda
A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make…
cs.LG2023
Observable Propagation: Uncovering Feature Vectors in Transformers
Jacob Dunefsky, Arman Cohan
A key goal of current mechanistic interpretability research in NLP is to find linear features (also called "feature vectors") for transformers: directions in activation space corre…