slavachalnev / SAE-TS
Improving Steering Vectors by Targeting Sparse Autoencoder Features
☆16Updated 4 months ago
Alternatives and similar repositories for SAE-TS:
Users that are interested in SAE-TS are comparing it to the libraries listed below
- Open source replication of Anthropic's Crosscoders for Model Diffing☆46Updated 4 months ago
- ☆10Updated 8 months ago
- ☆32Updated 4 months ago
- A library for efficient patching and automatic circuit discovery.☆59Updated last month
- ☆71Updated this week
- ☆26Updated 11 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 10 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆30Updated 9 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆14Updated 5 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆163Updated this week
- ☆61Updated 4 months ago
- Sparse Autoencoder Training Library☆43Updated 4 months ago
- Algebraic value editing in pretrained language models☆63Updated last year
- ☆30Updated 10 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆90Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆131Updated 10 months ago
- ☆34Updated 3 weeks ago
- Redwood Research's transformer interpretability tools☆14Updated 2 years ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆91Updated last year
- ☆82Updated 7 months ago
- ☆150Updated 2 weeks ago
- ☆211Updated 5 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆21Updated last month
- General-purpose activation steering library☆52Updated 2 months ago
- ☆23Updated last month
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆42Updated 5 months ago
- Experiments with representation engineering☆11Updated last year
- ☆121Updated last year
- ☆90Updated last month
- Applying SAEs for fine-grained control☆14Updated 3 months ago