yash-srivastava19 / arrakis
Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.
☆20Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for arrakis
- Open source replication of Anthropic's Crosscoders for Model Diffing☆13Updated 2 weeks ago
- Measuring the situational awareness of language models☆33Updated 8 months ago
- ☆99Updated 3 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆64Updated last month
- Sparse and discrete interpretability tool for neural networks☆53Updated 8 months ago
- we got you bro☆32Updated 3 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆17Updated 10 months ago
- Understanding how features learned by neural networks evolve throughout training☆31Updated 2 weeks ago
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆46Updated last week
- ☆24Updated 7 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
- Code for minimum-entropy coupling.☆29Updated 4 months ago
- ☆14Updated 7 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆56Updated 2 months ago
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆92Updated last week
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆29Updated 8 months ago
- Textbook on reinforcement learning from human feedback☆74Updated last week
- A library for efficient patching and automatic circuit discovery.☆30Updated last month
- ☆99Updated this week
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆55Updated 5 months ago
- A mechanistic approach for understanding and detecting factual errors of large language models.☆39Updated 4 months ago
- ☆27Updated last year
- Repository for the code of the "PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided Decoding" paper, NAACL'22☆64Updated 2 years ago
- PyTorch implementation for MRL☆18Updated 8 months ago
- ☆68Updated 2 months ago
- Experiments with representation engineering☆10Updated 8 months ago
- https://footprints.baulab.info☆12Updated last month
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆61Updated 4 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆62Updated last year