Acyclic Causal Model

Consists of input, intermediate, and output variables with associated causal mechanisms; the mathematical object central to DAS.

Neighborhood — ranked by edge-count

concept

Alignment Between High-Level and Low-Level Models
associated_with
A mapping assigning to each high-level variable a set of low-level variables and a function from low-level to high-level values.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Deterministic Causal Modelconcept0.807
Formal representation of algorithms as directed acyclic graphs computing functions f_A
dynamic causal modelsconcept0.797
Nonlinear models of brain dynamics that can be inverted via DEM.
Causal abstractionconcept0.782
A framework the paper uses alongside feature geometry to deepen mechanistic understanding of LMs
Causal Mechanismconcept0.753
Function determining the value of a variable based on its causal parents in an acyclic causal model.
Constructive Causal Abstractionconcept0.753
Formal definition: H is a constructive abstraction of L under alignment Π when interchange interventions have equivalent effects at both levels.
CausalGymframework0.753
Multi-task benchmark of linguistic behaviours for measuring causal efficacy of interpretability methods, adapted from SyntaxGym
Causal Mediation of Model Outputsconcept0.749
The extent to which a probe direction, when intervened upon, actually changes model outputs — contrasted with mere classification accuracy
Causal Abstraction over Cyclic Tasksconcept0.747