ApolloResearch / sampleLinks
Repository with sample code using Apollo's suggested engineering practices
☆9Updated 5 months ago
Alternatives and similar repositories for sample
Users that are interested in sample are comparing it to the libraries listed below
Sorting:
- Decoder only transformer, built from scratch with PyTorch☆30Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆10Updated 10 months ago
- (Model-written) LLM evals library☆18Updated 5 months ago
- Redwood Research's transformer interpretability tools☆15Updated 3 years ago
- ☆31Updated last year
- Attribution-based Parameter Decomposition☆23Updated this week
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 6 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated last year
- ☆43Updated 6 months ago
- ☆28Updated last year
- Tools for studying developmental interpretability in neural networks.☆91Updated 4 months ago
- ☆62Updated last week
- Inference API for many LLMs and other useful tools for empirical research☆47Updated last week
- METR Task Standard☆147Updated 4 months ago
- A small package implementing some useful wrapping around nnsight☆13Updated last month
- ☆14Updated 2 weeks ago
- Sparse Autoencoder Training Library☆50Updated last month
- A benchmark for mechanistic discovery of circuits in Transformers☆14Updated 5 months ago
- A quick way to get started with Transformer Lens☆14Updated last year
- A python sdk for LLM finetuning and inference on runpod infrastructure☆11Updated last week
- ☆120Updated 6 months ago
- Harmonic Datasets☆40Updated 10 months ago
- ☆22Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated last year
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆94Updated this week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- ☆10Updated 6 months ago