Insights into Galaxy Evolution from Interpretable Sparse Feature Networks
John F. Wu 2025 ApJ 980 183 A novel neural network architecture produces interpretable features that can be combined to estimate galaxy properties such as metallicity from pixel-level features. The…
Read the full articleYou might also wanna read
Machine Learning Validates Unrecognized Transient Astronomical Phenomena in Historical Observatory Images
Transient, star-like point sources that appear and vanish over short timescales are described in astronomical images prior to launch of Sput
arxiv.org·2mo ago
Anthropic researchers extract interpretable features from Claude 3 Sonnet using sparse autoencoders
We demonstrate that sparse autoencoders can extract interpretable features from Claude 3 Sonnet, a production-scale language model, addressi
arxiv.org·1mo ago
Decoding AI's Internal Language: How Sparse Autoencoders Help Interpret Neural Activations
Turning Claude's thoughts into text
anthropic.com·2mo ago
Understanding Linear Representations and Superposition in Large Language Model Interpretability
As LLMs become larger, more capable, and more ubiquitous, the field of mechanistic interpretability -- that is, understanding the inner wor.
ternarysearch.blogspot.com·4mo ago502 Bad Gateway
Secrets of Galaxy MergersDeep in the cosmic wilderness, astronomers are unlocking the hidden drama of how galaxies grow — by dissecting a ti
Study Reveals Convergent Evolution in How Language Models Learn Number Representations
Language models trained on natural text learn to represent numbers using periodic features with dominant periods at $T=2, 5, 10$. In this pa
arxiv.org·2mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.