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 6 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆62Updated this week
- ☆24Updated 7 months ago
- ☆105Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆64Updated last month
- Mechanistic Interpretability Visualizations using React☆196Updated 3 months ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆84Updated 8 months ago
- ☆100Updated 3 months ago
- we got you bro☆32Updated 3 months ago
- ☆102Updated last month
- Tools for studying developmental interpretability in neural networks.☆75Updated this week
- Sparse Autoencoder Training Library☆26Updated 2 weeks ago
- Erasing concepts from neural representations with provable guarantees☆208Updated 3 weeks ago
- ☆108Updated last year
- ☆18Updated this week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆96Updated 2 years ago
- METR Task Standard☆122Updated last week
- Harmonic Datasets☆32Updated 4 months ago
- Improving Alignment and Robustness with Circuit Breakers☆152Updated last month
- gzip Predicts Data-dependent Scaling Laws☆32Updated 5 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆186Updated last week
- 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
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- ☆54Updated 2 years ago
- ☆60Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆177Updated 5 months ago
- Measuring the situational awareness of language models☆33Updated 9 months ago
- Functional Benchmarks and the Reasoning Gap☆78Updated last month
- Using sparse coding to find distributed representations used by neural networks.☆181Updated last year
- Sparse and discrete interpretability tool for neural networks☆54Updated 9 months ago