Alternatives and similar repositories for interpretability-theory

Users that are interested in interpretability-theory are comparing it to the libraries listed below

• facebookresearch / ModelRatatouille
  Recycling diverse models
  ☆44Updated 2 years ago
• JonasGeiping / dataaugs
  ☆18Updated 2 years ago
• MadryLab / modeldiff
  ModelDiff: A Framework for Comparing Learning Algorithms
  ☆56Updated last year
• AndyShih12 / LongHorizonTemperatureScaling
  PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023
  ☆20Updated 2 years ago
• shoaibahmed / metadata_archaeology
  Official code for the paper: "Metadata Archaeology"
  ☆19Updated 2 years ago
• alexrame / diwa
  DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization
  ☆31Updated 2 years ago
• stanislavfort / adversaries_to_OOD_detection
  ☆12Updated 2 years ago
• izmailovpavel / spurious_feature_learning
  ☆45Updated 2 years ago
• socialfoundations / benchbench
  BenchBench is a Python package to evaluate multi-task benchmarks.
  ☆15Updated 10 months ago
• ml-jku / quam
  Quantification of Uncertainty with Adversarial Models
  ☆29Updated last year
• noranta4 / ASIF
  Personal implementation of ASIF by Antonio Norelli
  ☆25Updated last year
• fgranese / DOCTOR
  Advances in Neural Information Processing Systems (NeurIPS 2021)
  ☆22Updated 2 years ago
• EleutherAI / features-across-time
  Understanding how features learned by neural networks evolve throughout training
  ☆34Updated 7 months ago
• SamsungSAILMontreal / PAPA
  Repository for the PopulAtion Parameter Averaging (PAPA) paper
  ☆26Updated last year
• google-research / jax-influence
  ☆60Updated 3 years ago
• JeanKaddour / LAWA
  Latest Weight Averaging (NeurIPS HITY 2022)
  ☆30Updated last year
• rmwu / sea-reproduce
  Sample, estimate, aggregate: A recipe for causal discovery foundation models
  ☆11Updated 11 months ago
• BatsResearch / nplm
  A weak supervision framework for (partial) labeling functions
  ☆16Updated 10 months ago
• microsoft / augmented-interpretable-models
  Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.
  ☆42Updated 3 months ago
• facebookresearch / BalancingGroups
  Simple data balancing baselines for worst-group-accuracy benchmarks.
  ☆42Updated last year
• EleutherAI / mdl
  Minimum Description Length probing for neural network representations
  ☆19Updated 4 months ago
• js-d / sim_metric
  ☆35Updated last year
• interpretml / LLM-Tabular-Memorization-Checker
  Testing Language Models for Memorization of Tabular Datasets.
  ☆33Updated 3 months ago
• google-deepmind / ssl_hsic
  ☆37Updated 10 months ago
• ykwon0407 / beta_shapley
  Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning (AISTATS 2022 Oral)
  ☆41Updated 2 years ago
• gregorbachmann / scaling_mlps
  ☆51Updated 11 months ago
• YannDubs / Invariant-Self-Supervised-Learning
  Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"
  ☆41Updated 2 years ago
• sjunhongshen / DASH
  ☆22Updated 2 years ago
• anndvision / quince
  Code for Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
  ☆22Updated 2 years ago
• google-research / imagenet-mistakes
  ☆18Updated 3 years ago