2 citations · 2 across the 4 of their papers we have counts for
4 papers
SAE-StatSteer: Statistical Consensus Feature Selection for Optimization-Free Activation Steering of Large Language Models
Oshayer Siddique, J. M Areeb Uzair Alam, Md Jobayer Rahman Rafy +3
Activation steering adds a residual-stream direction at inference time, providing lightweight behavioral control without fine-tuning. Sparse autoencoders (SAEs) can make such inter…
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Adly Templeton, Tom Conerly, Jonathan Marcus +23
We demonstrate that sparse autoencoders can extract interpretable features from Claude 3 Sonnet, a production-scale language model, addressing the open question of whether dictiona…
Word Equations: Inherently Interpretable Sparse Word Embeddingsthrough Sparse Coding
Adly Templeton
Word embeddings are a powerful natural language processing technique, but they are extremely difficult to interpret. To enable interpretable NLP models, we create vectors where eac…
Exploring Sentence Vector Spaces through Automatic Summarization
Adly Templeton, Jugal Kalita
Given vector representations for individual words, it is necessary to compute vector representations of sentences for many applications in a compositional manner, often using artif…