TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Miscellaneous/Interpretability Techniques for Deep Learning/CausalGym

Interpretability Techniques for Deep Learning on CausalGym

Metric: Log odds-ratio (pythia-6.9b) (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Log odds-ratio (pythia-6.9b)▼Extra DataPaperDate↕Code
1DAS9.95NoCausalGym: Benchmarking causal interpretability ...2024-02-19Code
2Linear probe3.42NoCausalGym: Benchmarking causal interpretability ...2024-02-19Code
3Difference-in-means2.91NoCausalGym: Benchmarking causal interpretability ...2024-02-19Code
4k-means1.87NoCausalGym: Benchmarking causal interpretability ...2024-02-19Code
5PCA1.81NoCausalGym: Benchmarking causal interpretability ...2024-02-19Code
6LDA0.27NoCausalGym: Benchmarking causal interpretability ...2024-02-19Code
7Random0.01NoCausalGym: Benchmarking causal interpretability ...2024-02-19Code