ENTITY
SAE features
SAE features
PulseAugur coverage of SAE features — every cluster mentioning SAE features across labs, papers, and developer communities, ranked by signal.
Total · 30d
1
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
1
2 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 2 TOTAL
-
SHAP attribution methods show weak causal faithfulness in language models
Researchers have evaluated the effectiveness of SHAP as an attribution method for sparse autoencoder (SAE) features in language models. Their study, using sentiment classification on the SST-2 benchmark with GPT-2 Small…
-
AI model interventions unreliable, new research finds
A new research paper demonstrates that interventions designed to suppress undesirable behaviors in AI models by manipulating Sparse Autoencoder (SAE) features are unreliable. The study shows that even when specific SAE …