Superposition disentanglement of neural representations reveals hidden alignment

The superposition hypothesis states that a single neuron within a population may participate in the representation of multiple features in order for the population to represent more features than the number of neurons. In neuroscience and AI, representational alignment metrics measure the extent to which different deep neural networks (DNNs) or DNNs and brains represent similar information. In this work, we explore a critical question: does superposition interact with alignment metrics in any undesirable way? We hypothesize that models which represent the same features in different superposition arrangements will interfere with predictive mapping metrics (semi-matching, soft-matching, linear regression), producing lower alignment than expected. We first develop a theory for how the strict permutation metrics are dependent on superposition arrangements. This is tested by training sparse autoencoders (SAEs) to disentangle superposition in toy models, where alignment scores are shown to typically increase when a model's base neurons are replaced with its sparse overcomplete latent codes. We find similar increases for DNN-DNN and DNN-brain linear regression alignment in the visual domain. Our results suggest that superposition disentanglement is necessary for mapping metrics to uncover the true representational alignment between neural populations.