yash-srivastava19 / arrakisLinks
Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.
☆29Updated last month
Alternatives and similar repositories for arrakis
Users that are interested in arrakis are comparing it to the libraries listed below
Sorting:
- An introduction to LLM Sampling☆78Updated 5 months ago
- Attribution-based Parameter Decomposition☆23Updated this week
- gzip Predicts Data-dependent Scaling Laws☆35Updated last year
- Sparse Autoencoder Training Library☆50Updated last month
- we got you bro☆35Updated 10 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆16Updated 7 months ago
- ☆49Updated 6 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆57Updated 9 months ago
- Simple repository for training small reasoning models☆31Updated 3 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- ☆131Updated 2 months ago
- LLM training in simple, raw C/CUDA☆14Updated 5 months ago
- LLM attention pattern visualizer☆10Updated last year
- ☆28Updated last year
- Prune transformer layers☆69Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆43Updated 6 months ago
- ☆14Updated last year
- ☆23Updated last year
- Compiling useful links, papers, benchmarks, ideas, etc.☆46Updated 2 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆76Updated last year
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆32Updated last month
- Collection of autoregressive model implementation☆85Updated last month
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆44Updated last year
- Engine for collecting, uploading, and downloading model activations☆18Updated 2 months ago
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- 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
- PyTorch implementation for MRL☆18Updated last year
- Measuring the situational awareness of language models☆35Updated last year
- ☆55Updated 3 weeks ago
- A quick way to get started with Transformer Lens☆14Updated last year