A Mechanistic Interpretability Study of an Astronomy Foundation Model
cs.LG, astro-ph.IM
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- How to use and interpret activation patching
- Multi-Modal Masked Autoencoders for Learning Image-Spectrum Associations for Galaxy Evolution and Cosmology
- The Hydra Effect: Emergent Self-repair in Language Model Computations
- DeepDISC-photoz: Deep Learning-Based Photometric Redshift Estimation for Rubin LSST
- Dissociating Decodability and Causal Use in Bracket-Sequence Transformers
- Re-envisioning Euclid Galaxy Morphology: Identifying and Interpreting Features with Sparse Autoencoders
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis