Local Sparsity Enables Unsupervised LLM Safety Detection
Proposes locally masked sparse-autoencoder anomaly detection that flags unsafe LLM outputs unsupervised, using only 1-2% of SAE neurons.
1 stories, newest first · one card per story
Proposes locally masked sparse-autoencoder anomaly detection that flags unsafe LLM outputs unsupervised, using only 1-2% of SAE neurons.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views