@inproceedings{mercorio-etal-2025-sfal,
    title = "{SFAL}: Semantic-Functional Alignment Scores for Distributional Evaluation of Auto-Interpretability in Sparse Autoencoders",
    author = "Mercorio, Fabio  and
      Pallucchini, Filippo  and
      Potert{\`i}, Daniele  and
      Serino, Antonio  and
      Seveso, Andrea",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.39/",
    pages = "576--583",
    ISBN = "979-8-89176-333-3",
    abstract = "Interpreting the internal representations of large language models (LLMs) is crucial for their deployment in real-world applications, impacting areas such as AI safety, debugging, and compliance. Sparse Autoencoders facilitate interpretability by decomposing polysemantic activation into a latent space of monosemantic features. However, evaluating the auto-interpretability of these features is difficult and computationally expensive, which limits scalability in practical settings. In this work, we propose SFAL, an alternative evaluation strategy that reduces reliance on LLM-based scoring by assessing the alignment between the semantic neighbourhoods of features (derived from auto-interpretation embeddings) and their functional neighbourhoods (derived from co-occurrence statistics).Our method enhances efficiency, enabling fast and cost-effective assessments. We validate our approach on large-scale models, demonstrating its potential to provide interpretability while reducing computational overhead, making it suitable for real-world deployment."
}