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:
- š§ Starter templates for doing interpretability researchā74Updated 2 years ago
- Tools for studying developmental interpretability in neural networks.ā111Updated 4 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paperā129Updated 3 years ago
- ā128Updated 2 years ago
- ā29Updated last year
- Attribution-based Parameter Decompositionā31Updated 4 months ago
- ā27Updated 2 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).ā222Updated 10 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMsā19Updated last year
- Sparse Autoencoder Training Libraryā55Updated 5 months ago
- Mechanistic Interpretability Visualizations using Reactā296Updated 10 months ago
- ā142Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffingā59Updated last year
- ā60Updated last month
- Redwood Research's transformer interpretability toolsā14Updated 3 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.ā211Updated this week
- 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
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.ā229Updated 2 months ago
- Open source interpretability artefacts for R1.ā163Updated 6 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models ā¦ā219Updated last week
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)ā20Updated 9 months ago
- Erasing concepts from neural representations with provable guaranteesā238Updated 9 months ago
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.ā31Updated 6 months ago
- Machine Learning for Alignment Bootcampā79Updated 3 years ago
- ā247Updated last year
- Mechanistic Interpretability for Transformer Modelsā53Updated 3 years ago
- Universal Neurons in GPT2 Language Modelsā30Updated last year
- Inference API for many LLMs and other useful tools for empirical researchā77Updated this week
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"ā79Updated 3 years ago
- ā74Updated 2 weeks ago