Alternatives and similar repositories for icl-dynamics

Users that are interested in icl-dynamics are comparing it to the libraries listed below

• KihoPark / linear_rep_geometry
  ☆116Updated 11 months ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆57Updated 3 months ago
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆30Updated last year
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆63Updated last year
• adamkarvonen / SAE_BoardGameEval
  ☆24Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 9 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆88Updated last month
• noanabeshima / matryoshka-saes
  ☆25Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆33Updated 8 months ago
• bartbussmann / BatchTopK
  Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)
  ☆60Updated 6 months ago
• mcleish7 / gemstone-scaling-laws
  Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)
  ☆32Updated 4 months ago
• jiahai-feng / binding-iclr
  ☆16Updated last year
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆241Updated 2 weeks ago
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆20Updated last year
• pomonam / kronfluence
  Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
  ☆178Updated 7 months ago
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆28Updated last year
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆47Updated last year
• berlino / seq_icl
  ☆53Updated last year
• neelnanda-io / Crosscoders
  ☆58Updated last year
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆78Updated 3 years ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆89Updated last year
• PAIR-code / pretraining-tda
  ☆32Updated 11 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆26Updated last year
• ApolloResearch / deception-detection
  ☆33Updated last year
• msakarvadia / AttentionLens
  Interpretating the latent space representations of attention head outputs for LLMs
  ☆36Updated last year
• TristanThrush / perplexity-correlations
  Simple and scalable tools for data-driven pretraining data selection.
  ☆29Updated 8 months ago
• DeqingFu / transformers-icl-second-order
  Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…
  ☆19Updated last year
• bilal-chughtai / rep-theory-mech-interp
  ☆28Updated 2 years ago
• Silent-Zebra / twisted-smc-lm
  ☆31Updated 10 months ago