SASE Caltech

PIs: Frederick Eberhardt (HSS Division), Ralph Adolphs (HSS, BBE Divisions) SASE: Iman Wahle (Scholar) and Jenna Kahn (Scholar)

SASE Caltech Current Scholar Projects Completed Scholar Projects Current GRA Projects Completed GRA Projects Projects Causal Feature Learning Unsupervised Formation of High-level Causal Hypotheses from Low-level Data PIs: Frederick Eberhardt ( HSS Division), Ralph Adolphs ( HSS , BBE Divisions) SASE: Iman Wahle (Scholar) and Jenna Kahn (Scholar) A key part of scientific discovery is understanding the causal relationships between variables. Researchers often ask how a change in one variable affects changes in another. In order to ask these questions, though, researchers must first decide what v

related reading

• Frederick Eberhardtits.caltech.edu
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• In-context Learning and Induction Headstransformer-circuits.pub
• Weakly supervised causal representation learningarxiv.org
• Causal Autoregressive Flowsarxiv.org
• Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research] — LessWronglesswrong.com
• Relating Graph Neural Networks to Structural Causal Modelsarxiv.org
• Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning — LessWronglesswrong.com
• [2207.14251] Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictionsarxiv.org
• How Causal Abstraction Underpins Computational Explanationarxiv.org
• [2508.11214] How Causal Abstraction Underpins Computational Explanationarxiv.org
• Uncovering Neural Geometry in Vision Models With Block-Sparse Featurizersgoodfire.ai