callummcdougall / TransformerLens-intro
☆11Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for TransformerLens-intro
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆13Updated 7 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆64Updated this week
- ☆24Updated 7 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆97Updated 2 years ago
- METR Task Standard☆126Updated 3 weeks ago
- Tools for studying developmental interpretability in neural networks.☆77Updated last week
- Mechanistic Interpretability Visualizations using React☆200Updated 4 months ago
- ☆106Updated last month
- ☆21Updated last week
- ☆44Updated last week
- ☆109Updated this week
- ☆25Updated 6 months ago
- ☆188Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆61Updated last week
- Harmonic Datasets☆32Updated 4 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆158Updated last month
- Erasing concepts from neural representations with provable guarantees☆210Updated last week
- we got you bro☆33Updated 3 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 6 months ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆84Updated 8 months ago
- Einsum with einops style variable names☆15Updated 6 months ago
- Improving Alignment and Robustness with Circuit Breakers☆154Updated 2 months ago
- ☆101Updated 3 months ago
- ☆54Updated 2 years ago
- Using sparse coding to find distributed representations used by neural networks.☆188Updated last year
- ☆61Updated last year
- Sparse and discrete interpretability tool for neural networks☆55Updated 9 months ago
- Extract full next-token probabilities via language model APIs☆229Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆65Updated this week
- Measuring the situational awareness of language models☆33Updated 9 months ago