15 citations · 35 across the 6 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
What Do Sparse Autoencoder Feature Discovery Scores Identify? From Activations to Interventions
Yifeng Guo, Yanran Li, Xiang Chen
Sparse autoencoder (SAE) features are typically discovered from how their activations co-vary with behaviour, yet they are often used through interventions such as steering or abla…
stat.ML2026
Beyond Importance: Interchange-Sobol Sensitivity Reveals Task-Specific Content Channels in Transformer Components
Yifeng Guo, Jin-Hong Du, Xiang Chen
Mechanistic interpretability methods summarize a transformer component by a single importance score, conflating two distinct roles: a component may matter because it transports tas…