SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders

Understand

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive.

• We introduce SAEmnesia, a supervised sparse autoencoder framework that overcomes this by enforcing one-to-one concept-neuron mappings.
• By systematically labeling concepts during training, our method achieves feature centralization, binding each concept to a single, interpretable neuron.
• This enables highly targeted and efficient concept erasure.