longtermrisk / openweightsLinks
A python sdk for LLM finetuning and inference on runpod infrastructure
☆12Updated this week
Alternatives and similar repositories for openweights
Users that are interested in openweights are comparing it to the libraries listed below
Sorting:
- Decoder only transformer, built from scratch with PyTorch☆31Updated last year
- Tools for studying developmental interpretability in neural networks.☆100Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- Mechanistic Interpretability Visualizations using React☆273Updated 7 months ago
- Inference API for many LLMs and other useful tools for empirical research☆63Updated this week
- ☆234Updated 10 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆120Updated 5 months ago
- ☆124Updated last year
- METR Task Standard☆157Updated 6 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- (Model-written) LLM evals library☆18Updated 7 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated 9 months ago
- 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
- ☆28Updated last year
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆82Updated this week
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- Attribution-based Parameter Decomposition☆28Updated last month
- A library for efficient patching and automatic circuit discovery.☆73Updated 2 weeks ago
- Experiments with representation engineering☆12Updated last year
- ☆32Updated last year
- Erasing concepts from neural representations with provable guarantees☆232Updated 6 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆220Updated last year
- Code for our paper "Localizing Lying in Llama"☆11Updated 3 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆128Updated 2 years ago
- ☆30Updated last year
- A library for mechanistic anomaly detection☆22Updated 7 months ago
- ☆109Updated 3 weeks ago
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Updated 6 months ago
- ☆15Updated 4 months ago