2025/05/18 by Nikhil Singh, Manuel Cherep, Singh, Nikhil +3 · 1 citation
Arts and Humanities · Computer Science · #Audio and Speech Processing (eess.AS) #Diverse Musicological Studies #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music Technology and Sound Studies #Music and Audio Processing #Sound (cs.SD) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2505.18186
openalex publication_date 2025/05/18 · openalex created_date 2025/09/28 · openalex updated_date 2026/07/28
The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of such content's structure through statistical learning alone. This offers a potentially new lens on theories of human-generated media. When internal representations align with traditional constructs (e.g. chord progressions in music), they show how such categories can emerge from statistical regularities; when they diverge, they expose limits of existing frameworks and patterns we may have overlooked but that nonetheless carry explanatory power. In this paper, focusing on autoregressive music generators, we introduce a method for discovering interpretable concepts using sparse autoencoders (SAEs), extracting interpretable features from the residual stream of a transformer model. We make this approach scalable and evaluable using automated labeling and validation pipelines. Our results reveal both familiar musical concepts and coherent but uncodified patterns lacking clear counterparts in theory or language. As an extension, we show such concepts can be used to steer model generations. Beyond improving model transparency, our work provides an empirical tool for uncovering organizing principles that have eluded traditional methods of analysis and synthesis.