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 researchā73Updated 2 years ago
- Tools for studying developmental interpretability in neural networks.ā101Updated 2 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paperā129Updated 2 years ago
- ā26Updated 2 years ago
- ā126Updated last year
- Attribution-based Parameter Decompositionā28Updated 2 months ago
- ā29Updated last year
- ā56Updated 3 weeks ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).ā212Updated 8 months ago
- Sparse Autoencoder Training Libraryā54Updated 3 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMsā19Updated 10 months ago
- A benchmark for mechanistic discovery of circuits in Transformersā16Updated 8 months ago
- Mechanistic Interpretability for Transformer Modelsā51Updated 3 years ago
- ā67Updated 2 weeks ago
- Mechanistic Interpretability Visualizations using Reactā280Updated 8 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffingā58Updated 10 months ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizationsā195Updated 3 years ago
- ā139Updated last week
- Erasing concepts from neural representations with provable guaranteesā232Updated 7 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¦ā206Updated last week
- Redwood Research's transformer interpretability toolsā14Updated 3 years ago
- ā238Updated 10 months 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
- Keeping language models honest by directly eliciting knowledge encoded in their activations.ā209Updated last week
- Universal Neurons in GPT2 Language Modelsā30Updated last year
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.ā88Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingfaceā122Updated 6 months ago
- ā32Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)ā19Updated 7 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.ā223Updated 2 weeks ago