amack315 / unsupervised-steering-vectorsLinks
☆31Updated last year
Alternatives and similar repositories for unsupervised-steering-vectors
Users that are interested in unsupervised-steering-vectors are comparing it to the libraries listed below
Sorting:
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- Sparse Autoencoder Training Library☆52Updated last month
- ☆43Updated 6 months ago
- Attribution-based Parameter Decomposition☆23Updated this week
- ☆28Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆103Updated 3 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 6 months ago
- ☆50Updated last month
- ☆97Updated last month
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆181Updated this week
- Applying SAEs for fine-grained control☆18Updated 5 months ago
- ☆96Updated 3 months ago
- Engine for collecting, uploading, and downloading model activations☆18Updated 2 months ago
- ☆83Updated 9 months ago
- Measuring the situational awareness of language models☆35Updated last year
- ☆121Updated last year
- ☆171Updated last month
- ☆28Updated 10 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated last year
- ☆33Updated 4 months ago
- ☆223Updated 8 months ago
- A small package implementing some useful wrapping around nnsight☆13Updated last month
- General-purpose activation steering library☆75Updated 3 weeks ago
- ☆124Updated 6 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆200Updated 5 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- ☆131Updated 2 months ago