Datasets › CausalGym

CausalGym

Introduced by Aryaman Arora et al. in CausalGym: Benchmarking causal interpretability methods on linguistic tasks19 Feb 2024 archive 2025-07-28

SyntaxGym, adapted for interventional interpretability.

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Interpretability Techniques for Deep Learning CausalGym DAS Log odds-ratio (pythia-6.9b) 9.95 CausalGym: Benchmarking causal interpretability methods... aryamanarora/causalgym +1 7 Compare

Papers archive 2025-07-28

1 shown of 1 paper with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 1. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
CausalGym: Benchmarking causal interpretability methods on linguistic tasks 2 7 19 Feb 2024 ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

MIT

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • CausalGym

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections