callummcdougall / sae_visualizer
☆24Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for sae_visualizer
- ☆105Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆157Updated last month
- ☆107Updated this week
- ☆44Updated this week
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆17Updated 10 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆25Updated 5 months ago
- A library for efficient patching and automatic circuit discovery.☆31Updated last month
- ☆101Updated 3 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆63Updated this week
- ☆44Updated last month
- Mechanistic Interpretability Visualizations using React☆198Updated 4 months ago
- Measuring the situational awareness of language models☆33Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆65Updated last month
- Universal Neurons in GPT2 Language Models☆27Updated 5 months ago
- we got you bro☆33Updated 3 months ago
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- ☆108Updated last year
- ☆145Updated 3 weeks ago
- ☆188Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆97Updated 5 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆26Updated 5 months ago
- ☆18Updated last week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆84Updated last week
- Sparse and discrete interpretability tool for neural networks☆55Updated 9 months ago
- Experiments with representation engineering☆10Updated 8 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆61Updated last week
- Erasing concepts from neural representations with provable guarantees☆209Updated last week
- ☆13Updated 2 months ago
- ☆26Updated last year
- Tools for studying developmental interpretability in neural networks.☆75Updated last week