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
- PyTorch implementation for MRL☆18Updated 9 months ago
- ☆14Updated 7 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆16Updated 3 weeks ago
- Sparse and discrete interpretability tool for neural networks☆55Updated 9 months ago
- Evaluation of neuro-symbolic engines☆33Updated 3 months ago
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆39Updated 10 months ago
- Understanding how features learned by neural networks evolve throughout training☆31Updated 3 weeks ago
- ☆41Updated 2 weeks 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
- Experiments on GPT-3's ability to fit numerical models in-context.☆14Updated 2 years ago
- gzip Predicts Data-dependent Scaling Laws☆32Updated 5 months ago
- Experiments with representation engineering☆10Updated 8 months ago
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆56Updated 5 months ago
- Genetics for Language Models☆12Updated 4 months ago
- Measuring the situational awareness of language models☆33Updated 9 months ago
- ☆107Updated this week
- Repository for the paper Stream of Search: Learning to Search in Language☆93Updated 3 months ago
- Minimum Description Length probing for neural network representations☆16Updated last week
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆17Updated 10 months ago
- Code for minimum-entropy coupling.☆30Updated 4 months ago
- Textbook on reinforcement learning from human feedback☆76Updated 3 weeks ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆58Updated 3 months ago
- A mechanistic approach for understanding and detecting factual errors of large language models.☆39Updated 4 months ago
- Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL☆43Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆65Updated last month
- ☆28Updated last year
- ☆24Updated 7 months ago
- ☆26Updated last year
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆17Updated 7 months ago
- LLM training in simple, raw C/CUDA☆12Updated last month