Dana Arad
- SAEs Are Good for Steering -- If You Select the Right Features
2025/05/26 by Dana Arad, Arad, Dana, Aaron Mueller +3 · 1 voice · 17 citations
Engineering · #cs.LG #cs.AI #cs.CL
- MIB: A Mechanistic Interpretability Benchmark
2025/04/17 by Aaron Mueller, Mueller, Aaron, Atticus Geiger +45 · 1 voice · 6 citations
Computer Science · #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI) #Topic Modeling #cs.AI #cs.CL #cs.LG