research
∙
09/12/2023
Circuit Breaking: Removing Model Behaviors with Targeted Ablation
Language models often exhibit behaviors that improve performance on a pr...
share
research
∙
08/29/2023
Measurement Tampering Detection Benchmark
When training powerful AI systems to perform complex tasks, it may be ch...
research
∙
07/27/2023
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) is a technique for tra...
research
∙
07/07/2023
Discovering Variable Binding Circuitry with Desiderata
Recent work has shown that computation in language models may be human-u...
research
∙
10/07/2021