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
☆34May 23, 2024Updated 2 years ago
Alternatives and similar repositories for elk-generalization
Users that are interested in elk-generalization are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- ☆22Nov 15, 2024Updated last year
- ☆30Jan 7, 2026Updated 9 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆51May 31, 2024Updated 2 years ago
- ☆17Jun 17, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- 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…☆14Jan 26, 2025Updated last year
- Decoder only transformer, built from scratch with PyTorch☆34Oct 22, 2023Updated 2 years ago
- A python sdk for LLM finetuning and inference on runpod infrastructure☆30Updated this week
- ☆15Jul 12, 2024Updated 2 years ago
- Understanding how features learned by neural networks evolve throughout training☆40Oct 24, 2024Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆24Oct 18, 2024Updated last year
- Codebase for Linguistic Collapse: Neural Collapse in (Large) Language Models [NeurIPS 2024] [arXiv:2405.17767]☆18Apr 14, 2025Updated last year
- ☆33Nov 11, 2025Updated 10 months ago
- A benchmark for mechanistic discovery of circuits in Transformers☆18Dec 15, 2024Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆225Sep 28, 2026Updated last week
- [WIP] Transformer to embed Danbooru labelsets☆13Mar 31, 2024Updated 2 years ago
- Easily deploy my zsh and tmux configuration on new machines. Includes local and remote aliases to improve workflow.☆16Apr 23, 2026Updated 5 months ago
- Erasing concepts from neural representations with provable guarantees☆269Jan 27, 2025Updated last year
- ☆36Jun 4, 2025Updated last year
- ☆10Aug 14, 2023Updated 3 years ago
- ☆11Sep 26, 2023Updated 3 years ago
- ☆26Jun 22, 2025Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆307Jul 20, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆225Oct 14, 2025Updated 11 months ago
- einsum via batch matrix multiply☆15Nov 29, 2023Updated 2 years ago
- ☆430Aug 21, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆276Feb 27, 2026Updated 7 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆58Oct 30, 2025Updated 11 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆279Updated this week
- A quick way to get started with Transformer Lens☆15Dec 13, 2023Updated 2 years ago
- ☆10Mar 24, 2025Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆74Jun 19, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Simple and scalable tools for data-driven pretraining data selection.☆31Jun 9, 2025Updated last year
- Code used for "Training Agents to Self-Report Misbehavior"☆19Feb 27, 2026Updated 7 months ago
- ☆30Aug 2, 2024Updated 2 years ago
- Find context neurons in Pythia models.☆13Jun 13, 2023Updated 3 years ago
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Sep 6, 2023Updated 3 years ago
- ☆10Oct 11, 2022Updated 3 years ago
- ☆13Aug 19, 2024Updated 2 years ago