FlyingPumba / InterpBenchLinks
A benchmark for mechanistic discovery of circuits in Transformers
☆16Updated last year
Alternatives and similar repositories for InterpBench
Users that are interested in InterpBench are comparing it to the libraries listed below
Sorting:
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆45Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- A library for efficient patching and automatic circuit discovery.☆88Updated last month
- Sparse Autoencoder Training Library☆56Updated 9 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆57Updated 3 months ago
- Tools for optimizing steering vectors in LLMs.☆19Updated 9 months ago
- Attribution-based Parameter Decomposition☆33Updated 7 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆26Updated last year
- ☆115Updated 11 months ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆55Updated this week
- ☆206Updated 3 months ago
- Trains Sparse Autoencoders based on outputs from language models☆11Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆241Updated last week
- ☆138Updated last year
- ☆20Updated 9 months ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆12Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- ☆143Updated last month
- Universal Neurons in GPT2 Language Models☆30Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆140Updated 11 months ago
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Updated last year
- ☆24Updated last year
- ☆36Updated last year
- ☆51Updated 2 years ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆20Updated 3 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆163Updated 7 months ago
- A tiny easily hackable implementation of a feature dashboard.☆15Updated 3 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆48Updated 4 months ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆30Updated 3 months ago