Can SAEs reveal and mitigate racial biases of LLMs in healthcare?

ICLR 2026 Conference Submission18067 Authors

Keywords: clinical natural language processing, mechanistic interpretability

TL;DR: We investigate whether SAEs can reveal racial bias as interpretable concepts in the clinical domain, and if they can help mitigate it

Abstract:

LLMs are increasingly being used in healthcare. This promises to free physicians from drudgery, enabling better care to be delivered at scale. But the use of LLMs in this space also brings risks; for example, such models may worsen existing biases. How can we spot when LLMs are (spuriously) relying on patient race to inform predictions? In this work we assess the degree to which Sparse Autoencoders (SAEs) can reveal (and control) associations the model has made between race and stigmatizing concepts.

We first identify SAE latents in gemma-2 models which appear to correlate with Black individuals. We find that this latent activates on reasonable input sequences (e.g., "African American") but also problematic words like "incarceration". We then show that we can use this latent to "steer" models to generate outputs about Black patients, and further that this can induce problematic associations in model outputs as a result. For example, activating the Black latent increases the risk assigned to the probability that a patient will become "belligerent". We also find that even in this controlled setting in which we causally intervene to manipulate only patient race, elicited CoT reasoning strings do not communicate that race is a factor in the resulting assessments. We evaluate the degree to which such "steering" via latents might be useful for mitigating bias. We find that this offers improvements in simple settings, but is less successful for more realistic and complex clinical tasks.

Primary Area: interpretability and explainable AI

Submission Number: 18067