SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanation

Abstract:One of the pivotal recent challenges in neural network interpretability is polysemanticity, where a single neuron is activated by multiple, often unrelated concepts, hindering clear functional understanding. Although prior work has explored this phenomenon, existing approaches remain architecture-specific and depend on manual heuristics such as a fixed number of concept clusters ($K$), limiting their generality and scalability--especially for modern Transformer-based models. To address these limitations, we introduce SPICE (\textbf{S}imple \textbf{P}olysemantic Feature \textbf{I}nterpretation via \textbf{C}lustering-based \textbf{E}xplanation), a generalizable framework for analyzing polysemanticity in deep vision architectures. SPICE avoids architecture-dependent propagation rules, enabling the first systematic comparison of polysemanticity across both CNNs and Transformers, and automatically determines the number of concept clusters per neuron, eliminating reliance on a preset $K$ and supporting scalable analysis for large models. Using SPICE, we conduct a comprehensive investigation into how polysemanticity emerges, varies across depth and architecture, and forms through distinct computational pathways.

Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)

arXiv:2609.13198 [cs.LG]

(or arXiv:2609.13198v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.13198 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.