paper
referenced-only
2025
paper:arxiv-2508-11214How causal abstraction underpins computational explanation
ByAtticus Geiger·Jacqueline Harding·Thomas Icard
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- ≈ 80%
- ≈ 78%
- Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to SemanticsJoshua Lum, Ziyi Liu, Dani Yogatama Isabelle Lee2024≈ 77%
- A macro agent and its actionsFrancesco Massari, Maggie Beheler-Amass and Giulio Tononi Larissa Albantakis2020≈ 77%
- ≈ 77%
- Explanations are a Means to an End: Decision Theoretic Explanation EvaluationBerk Ustun, Jessica Hullman Ziyang Guo2026≈ 76%
- Combining Causal Models for More Accurate Abstractions of Neural NetworksSara Magliacane, Atticus Geiger Theodora-Mara P\^islar2025≈ 76%
- CausalARC: Abstract Reasoning with Causal World ModelsJohn Kalantari, Kia Khezeli Jacqueline Maasch2026≈ 76%
- Grounding Before Generalizing: How AI Differs from Humans in Causal TransferYuxi Ma, Zhihao Cao, Yixin Zhu, Song-Chun Zhu Liangru Xiang2026≈ 76%
- Discovering and Reasoning of Causality in the Hidden World with Large Language ModelsYongqiang Chen, Tongliang Liu, Mingming Gong, James Cheng, Bo Han, Kun Zhang Chenxi Liu2025≈ 75%
- Morphological Computing as Logic Underlying Cognition in Human, Animal, and Intelligent MachineGordana Dodig-Crnkovic2023≈ 75%
- Hume's Representational Conditions for Causal Judgment: What Bayesian Formalization Abstracted AwayYiling Wu2026≈ 75%
- Causal Foundations of Collective AgencySebastian Weichwald, Lewis Hammond Frederik Hytting J{\o}rgensen2026≈ 75%
- ≈ 75%
- Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language ExplanationsAjay Pravin Mahale2026≈ 75%
- Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studiesin corpus2023≈ 73%
- Cognitive glues are shared models of relative scarcities: the economics of collective intelligencein corpus2026≈ 71%
- Finger Exercises in Formal Concept Analysisin corpus2006≈ 71%
- ≈ 70%
- ≈ 70%
- The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?in corpus2025≈ 70%
- Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representationsin corpus2023≈ 70%
- The Machine Consciousness Hypothesisin corpus≈ 70%
- ≈ 69%
- ≈ 69%
- ≈ 69%
- ≈ 68%
- ≈ 68%
Similar preprints — Semantic Scholar
Cited by (2)
- Addressing divergent representations from causal interventions on neural networks
Causal intervention methods central to mechanistic interpretability—including activation patching, mean-difference vector patching, Sparse Autoencoders, and Distributed Alignment Search (DAS)—systemat
- Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
Llama-3.1-8B solves cyclic arithmetic (e.g., "what month is six months after August?") not by performing modular addition in the period of the cyclic concept (12 for months, 7 for days of the week) as