3 papers
cs.LG2025
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
Xiangchen Song, Aashiq Muhamed, Yujia Zheng +5
Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration…
cs.LG2024
Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models
Aashiq Muhamed, Mona Diab, Virginia Smith
Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have em…
cs.LG2024
Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients
Aashiq Muhamed, Oscar Li, David Woodruff +2
Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory. While existing projection-based optimization methods address this by projecting gra…