Stochastic Parameter Decomposition

N/A

# link_n87icxthf6.pdf ## Metadata - PDFFormatVersion=1.5 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - Author=Lucius Bushnaq; Dan Braun; Lee Sharkey - Creator=arXiv GenPDF (tex2pdf:) - Custom.DOI=https://doi.org/10.48550/arXiv.2506.20790 - Custom.License=http://creativecommons.org/licenses/by/4.0/ - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) kpathsea version 6.3.5 - Custom.arXivID=https://arxiv.org/abs/2506.20790v2 - Producer=pikepdf 8.15.1 - Title=Stochastic Parameter De

saved by

• Yudhister Joel Kumar
• Logan Graves

related reading

• 2501.14926arxiv.org
• Towards Scalable Parameter Decompositiongoodfire.ai
• Attribution-based parameter decomposition — LessWronglesswrong.com
• Stochastic Parameter Decompositionarxiv.org
• [2506.20790] Stochastic Parameter Decompositionarxiv.org
• [2604.06366] Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networksarxiv.org
• Towards Scalable Parameter Decompositiongoodfire.ai
• arxiv.org/pdf/1805.08522arxiv.org
• Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decompositionarxiv.org
• Interpreting Language Model Parametersgoodfire.ai
• [2501.14926] Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decompositionarxiv.org
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub