FlyingPumba / InterpBenchLinks
A benchmark for mechanistic discovery of circuits in Transformers
☆16Updated 11 months ago
Alternatives and similar repositories for InterpBench
Users that are interested in InterpBench are comparing it to the libraries listed below
Sorting:
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆25Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆42Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆60Updated last year
- Sparse Autoencoder Training Library☆55Updated 6 months ago
- Universal Neurons in GPT2 Language Models☆31Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated 3 weeks ago
- A library for efficient patching and automatic circuit discovery.☆80Updated 3 months ago
- Tools for optimizing steering vectors in LLMs.☆14Updated 7 months ago
- Attribution-based Parameter Decomposition☆31Updated 5 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
- ☆194Updated last month
- ☆129Updated last year
- ☆136Updated this week
- ☆19Updated 7 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆141Updated 4 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆225Updated last week
- A tiny easily hackable implementation of a feature dashboard.☆15Updated last month
- Unified access to Large Language Model modules using NNsight☆59Updated this week
- ☆110Updated 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 9 months ago
- ☆36Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆50Updated 11 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆26Updated 9 months ago
- 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
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆20Updated 3 weeks ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆129Updated 8 months ago
- ☆61Updated last month
- ☆132Updated 2 years ago
- ☆56Updated last year
- ☆94Updated last year