jacobdunefsky / transcoder_circuits
☆33Updated 3 months ago
Related projects: ⓘ
- ☆75Updated this week
- ☆54Updated last week
- Sparse Autoencoder Training Library☆18Updated last month
- ☆99Updated 10 months ago
- Universal Neurons in GPT2 Language Models☆25Updated 3 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆133Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆57Updated last week
- ☆110Updated 3 weeks ago
- ☆68Updated 7 months ago
- Mechanistic Interpretability for Transformer Models☆48Updated 2 years ago
- ☆24Updated 5 months ago
- ☆91Updated last month
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆14Updated 8 months ago
- ☆174Updated 4 months ago
- Sparse and discrete interpretability tool for neural networks☆51Updated 7 months ago
- Using sparse coding to find distributed representations used by neural networks.☆162Updated 10 months ago
- Algebraic value editing in pretrained language models☆54Updated 10 months ago
- Mechanistic Interpretability Visualizations using React☆175Updated 2 months ago
- ☆48Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆83Updated 3 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆22Updated 3 months ago
- Sparse probing paper full code.☆47Updated 9 months ago
- ☆50Updated last year
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆165Updated last year
- ☆66Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆52Updated last month
- we got you bro☆32Updated last month
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆76Updated 3 weeks ago
- ☆64Updated last month
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆26Updated last month