all AI news
PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits
April 10, 2024, 4:42 a.m. | Maximilian Dreyer, Erblina Purelku, Johanna Vielhaben, Wojciech Samek, Sebastian Lapuschkin
cs.LG updates on arXiv.org arxiv.org
Abstract: The field of mechanistic interpretability aims to study the role of individual neurons in Deep Neural Networks. Single neurons, however, have the capability to act polysemantically and encode for multiple (unrelated) features, which renders their interpretation difficult. We present a method for disentangling polysemanticity of any Deep Neural Network by decomposing a polysemantic neuron into multiple monosemantic "virtual" neurons. This is achieved by identifying the relevant sub-graph ("circuit") for each "pure" feature. We demonstrate how …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
#13721 - Data Engineer - AI Model Testing
@ Qualitest | Miami, Florida, United States
Elasticsearch Administrator
@ ManTech | 201BF - Customer Site, Chantilly, VA