EleutherAI / elk-generalizationLinks
Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from easy questions to hard
☆28Updated last year
Alternatives and similar repositories for elk-generalization
Users that are interested in elk-generalization are comparing it to the libraries listed below
Sorting:
- A library for efficient patching and automatic circuit discovery.☆73Updated 2 weeks ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- Sparse Autoencoder Training Library☆54Updated 3 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
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆200Updated this week
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆119Updated 5 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆112Updated last month
- ☆89Updated 11 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆12Updated last year
- ☆62Updated last week
- ☆121Updated last year
- ☆123Updated last year
- A library for mechanistic anomaly detection☆22Updated 6 months ago
- ☆107Updated 2 weeks ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆113Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 8 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆52Updated 10 months ago
- Attribution-based Parameter Decomposition☆28Updated last month
- ☆23Updated 6 months ago
- ☆94Updated 3 months ago
- ☆137Updated last week
- ☆28Updated last year
- ☆183Updated 3 weeks ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated 9 months ago