redwoodresearch / remix_publicLinks
☆19Updated 2 years ago
Alternatives and similar repositories for remix_public
Users that are interested in remix_public are comparing it to the libraries listed below
Sorting:
- Tools for studying developmental interpretability in neural networks.☆91Updated 4 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆204Updated last week
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- (Model-written) LLM evals library☆18Updated 5 months ago
- ☆63Updated 2 years ago
- Einsum with einops style variable names☆16Updated last year
- A python sdk for LLM finetuning and inference on runpod infrastructure☆11Updated this week
- Redwood Research's transformer interpretability tools☆15Updated 3 years ago
- we got you bro☆35Updated 10 months ago
- ☆28Updated last year
- Erasing concepts from neural representations with provable guarantees☆228Updated 4 months ago
- METR Task Standard☆148Updated 4 months ago
- Mechanistic Interpretability Visualizations using React☆253Updated 5 months ago
- ☆31Updated last year
- The Happy Faces Benchmark☆15Updated last year
- ☆9Updated 9 months ago
- ☆223Updated 8 months ago
- See the issue board for the current status of active and prospective projects!☆65Updated 3 years ago
- A dataset of alignment research and code to reproduce it☆77Updated last year
- Machine Learning for Alignment Bootcamp☆25Updated last year
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆214Updated last year
- Machine Learning for Alignment Bootcamp (MLAB).☆30Updated 3 years ago
- ☆121Updated last year
- Machine Learning for Alignment Bootcamp☆73Updated 3 years ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆94Updated this week
- Measuring the situational awareness of language models☆35Updated last year
- ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…☆60Updated this week
- ☆96Updated 2 months ago
- ☆76Updated last month
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated last year