{"slug": "a-deeper-analysis-of-block-sparse-featurizers", "title": "A Deeper Analysis of Block-Sparse Featurizers", "summary": "A new analysis of the block-sparse featurizer (BSF), introduced by Fel et al. in 2026, finds it still suffers from classic sparse autoencoder failure modes like feature splitting and composition, despite its design for low-dimensional manifold features common in vision. The authors propose architectural changes, including a Tournament Top-K selection rule that significantly reduces feature splitting, and extend the block paradigm to the crosscoder.", "body_md": "# Computer Science > Machine Learning\n\n[Submitted on 27 Aug 2026]\n\n# Title:A Deeper Analysis of Block-Sparse Featurizers\n\n[View PDF](/pdf/2608.27515)\n\n[HTML (experimental)](https://arxiv.org/html/2608.27515v1)\n\nAbstract:The recently introduced block-sparse featurizer (BSF; Fel et al., 2026) is similar to a sparse autoencoder (SAE), but its atomic unit is a small subspace (a block of directions) rather than a single direction. It is designed for features that live on low-dimensional manifolds, which are especially frequent in vision. This work studies the BSF's strengths and weaknesses, finding how it still somewhat suffers from classic SAE failure modes, like feature splitting and composition. We propose several architectural changes to the BSF, including a Tournament Top-K selection rule that significantly reduces feature splitting, and we also extend the block paradigm to the crosscoder.\n\n## Submission history\n\nFrom: Alexandru-Iulius Jerpelea [[view email](/show-email/5f30d5d2/2608.27515)]\n\n**[v1]** Thu, 27 Aug 2026 09:50:20 UTC (1,239 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/a-deeper-analysis-of-block-sparse-featurizers", "canonical_source": "https://arxiv.org/abs/2608.27515", "published_at": "2026-08-31 04:00:00+00:00", "updated_at": "2026-08-31 04:23:09.394780+00:00", "lang": "en", "topics": ["machine-learning", "artificial-intelligence", "ai-research"], "entities": ["Fel et al.", "block-sparse featurizer", "sparse autoencoder", "Tournament Top-K", "crosscoder"], "alternates": {"html": "https://wpnews.pro/news/a-deeper-analysis-of-block-sparse-featurizers", "markdown": "https://wpnews.pro/news/a-deeper-analysis-of-block-sparse-featurizers.md", "text": "https://wpnews.pro/news/a-deeper-analysis-of-block-sparse-featurizers.txt", "jsonld": "https://wpnews.pro/news/a-deeper-analysis-of-block-sparse-featurizers.jsonld"}}