Sparse autoencoders applied to Neural Quantum States extract unsupervised features correlating with and causally steering physical observables such as order parameters while preserving variational energy.
Causal Abstractions of Neural Networks
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Authors create a benchmark across discrete/continuous and static/dynamical systems and introduce the Causal Abstraction Error (CAE) metric that reliably distinguishes valid from invalid causal abstractions when it includes faithfulness testing.
Semantic constituency graphs outperform syntactic constituency and dependency structures from seven formalisms when added to a Transformer for language modeling.
Activation patching provides evidence about neural network circuits when the choice of metric is aligned with the hypothesis and common interpretation errors are avoided.
citing papers explorer
-
Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders
Sparse autoencoders applied to Neural Quantum States extract unsupervised features correlating with and causally steering physical observables such as order parameters while preserving variational energy.
-
Validating Causal Abstraction Metrics on Simulated Complex Systems
Authors create a benchmark across discrete/continuous and static/dynamical systems and introduce the Causal Abstraction Error (CAE) metric that reliably distinguishes valid from invalid causal abstractions when it includes faithfulness testing.
-
Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling
Semantic constituency graphs outperform syntactic constituency and dependency structures from seven formalisms when added to a Transformer for language modeling.
-
How to use and interpret activation patching
Activation patching provides evidence about neural network circuits when the choice of metric is aligned with the hypothesis and common interpretation errors are avoided.