An open-source tool is developed for mechanistic interpretability of AI weather models, demonstrated on GraphCast by identifying latent directions corresponding to interpretable weather features.
arXiv preprint arXiv:2406.17759 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
Mechanistic Interpretability Tool for AI Weather Models
An open-source tool is developed for mechanistic interpretability of AI weather models, demonstrated on GraphCast by identifying latent directions corresponding to interpretable weather features.
- WriteSAE: Sparse Autoencoders for Recurrent State