Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Current feature description methods face two critical challenges: limited robustness and the flawed assumption that each neuron encodes only a single concept (monosemanticity), despite growing evidence that neurons are often polysemantic. This assumption restricts the expressiveness of feature descriptions and limits their ability to capture the full range of behaviors encoded in model internals. To address this, we introduce Polysemantic FeatuRe Identification and Scoring Method (PRISM), a novel framework that captures the inherent complexity of neural network features. Unlike prior approaches that assign a single description per feature, PRISM provides more nuanced descriptions for both polysemantic and monosemantic features. We apply PRISM to language models and, through extensive benchmarking against existing methods, demonstrate that our approach produces more accurate and faithful feature descriptions, improving both overall description quality (via a description score) and the ability to capture distinct concepts when polysemanticity is present (via a polysemanticity score).

View on arXiv

@article{kopf2025_2506.15538,
  title={ Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework },
  author={ Laura Kopf and Nils Feldhus and Kirill Bykov and Philine Lou Bommer and Anna Hedström and Marina M.-C. Höhne and Oliver Eberle },
  journal={arXiv preprint arXiv:2506.15538},
  year={ 2025 }
}

Comments on this paper