arXiv Machine Learning
PhysSAE: Mechanistic Interpretability with Sparse Autoencoders
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
3d ago
PhysSAE: Mechanistic Interpretability of PINNs with Sparse Autoencoders
arXiv:2609.07061v2 Announce Type: replace Abstract: Physics-Informed Neural Networks (PINNs) embed PDE residuals into neural network training, but their internal representations remain opaque: it is...
arXiv Machine Learning
Jul 15
From Geometric Recovery to Causal Validation: A Reproducible Audit of Sparse Autoencoder Features, from Superposition Geometry to Causal Inertness
arXiv:2607. 12166v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are the standard for decomposing superposed neural representations into interpretable features, and evaluation relies predominantly on correlational recovery metrics -- cosine similarity between ground-truth directions and decoder atoms.
arXiv AI
Jul 3
Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders
arXiv:2607. 01336v1 Announce Type: cross Abstract: Neural Quantum States (NQS) are a remarkably expressive class of variational ans\"atze for quantum many-body wavefunctions, yet little is understood about their internal mechanisms: trained on variational objectives alone, how do NQS accurately capture physical observables that they have never been explicitly optimized for?
arXiv Machine Learning
Aug 27
Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders
The paper applies sparse autoencoders to a neutrino foundation model trained on IceCube data, uncovering a validated atlas of physical concepts within the model’s internal representation. Causal analysis shows the direction reconstruction head largely ignores this atlas, whereas an uncertainty head trained on the same representation effectively uses quality and brightness features, improving angular resolution from 20.2° to 3.2° at 20% efficiency. These findings demonstrate that mechanistic interpretability can expose latent physics and guide the design of downstream tasks.
arXiv AI
Jun 11
Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics
arXiv:2606. 11657v1 Announce Type: cross Abstract: Generative AI emulators are increasingly used in scientific domains where we already have strong theory, benchmarks, and physical intuition.
arXiv Machine Learning
Jul 9
Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories
arXiv:2607. 07127v1 Announce Type: cross Abstract: Lattice field theory is the workhorse of non-perturbative physics, used to simulate phenomena from the strong nuclear force to critical phenomena in materials.