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.
https://www.transformer-circuits.pub/2022/mech-interp-essay (June 27 2022), accessed: 2026-02-13
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.ao-ph 1years
2026 1verdicts
UNVERDICTED 1representative 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.