Evaluating feature steering: A case study in mitigating social biases

This post details a case study on using feature steering to mitigate social biases in Claude 3 Sonnet. It quantifies the effects of steering 29 features related to social biases on bias and capabilities evaluations (MMLU, PubMedQA, BBQ, model-written evals). Key findings include the identification of a 'steering sweet spot' (-5 to 5) where capabilities are preserved, the observation of targeted influence on specific biases (e.g., gender, political stances), and the discovery of 'off-target effects' where steering one feature impacts unrelated biases (e.g., gender feature affecting age bias). A 'neutrality feature' is identified as a promising method for reducing multiple social biases with minimal impact on capabilities. The post also discusses limitations related to feature labeling accuracy and the computational cost of evaluations.