thestephencasper / everything-you-needLinks
we got you bro
ā36Updated last year
Alternatives and similar repositories for everything-you-need
Users that are interested in everything-you-need are comparing it to the libraries listed below
Sorting:
- Tools for studying developmental interpretability in neural networks.ā105Updated 3 months ago
- š§ Starter templates for doing interpretability researchā74Updated 2 years ago
- ā29Updated last year
- ā127Updated last year
- Attribution-based Parameter Decompositionā30Updated 3 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paperā129Updated 3 years ago
- Sparse Autoencoder Training Libraryā54Updated 5 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).ā221Updated 9 months ago
- ā27Updated 2 years ago
- Open source replication of Anthropic's Crosscoders for Model Diffingā59Updated 11 months ago
- Mechanistic Interpretability Visualizations using Reactā291Updated 9 months ago
- Redwood Research's transformer interpretability toolsā14Updated 3 years ago
- Erasing concepts from neural representations with provable guaranteesā236Updated 8 months ago
- ā142Updated 3 weeks ago
- ā58Updated last week
- Keeping language models honest by directly eliciting knowledge encoded in their activations.ā209Updated 2 weeks ago
- Mechanistic Interpretability for Transformer Modelsā53Updated 3 years ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from eā¦ā28Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models ā¦ā215Updated this week
- A collection of different ways to implement accessing and modifying internal model activations for LLMsā19Updated 11 months ago
- ā242Updated last year
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.ā31Updated 5 months ago
- Utilities for the HuggingFace transformers libraryā72Updated 2 years ago
- ā34Updated last year
- Extract full next-token probabilities via language model APIsā247Updated last year
- Sparse and discrete interpretability tool for neural networksā63Updated last year
- Universal Neurons in GPT2 Language Modelsā30Updated last year
- ā71Updated last month
- Open source interpretability artefacts for R1.ā160Updated 5 months ago
- METR Task Standardā162Updated 8 months ago