Seonglae ChoSAE Unlearning Methods
Sparse Autoencoders for Improving Unlearning in Large Language Models
A.K.A: Smallish Large-Language Models: What Do They Know? Can They Un-Know Things?? Let’s Find Out.
https://www.kelechin.com/unlearning1
Limitation
SAE for unlearning concepts were not really helpful
Interventions aimed at removing specific knowledge led to performance degradation in domains unrelated to biology, and the loss itself increased in texts like openwebtext. Compared to negative scaling, clamping had fewer side effects and was more effective.
Impressive examples that fix LLM reasoning errors
Monitor: An AI-Driven Observability Interface
This write-up is a technical demonstration, which describes and evaluates the use of a new piece of technology. For technical demonstrations, we still run systematic experiments to test our findings, but do not run detailed ablations and controls. The claims are ones that we have tested and stand behind, but have not vetted as thoroughly as in our research reports.
https://transluce.org/observability-interface
Demo
