Understanding how features learned by neural networks evolve throughout training
☆40Oct 24, 2024Updated 2 years ago
Alternatives and similar repositories for features-across-time
Users that are interested in features-across-time are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆34May 23, 2024Updated 2 years ago
- ☆16Oct 14, 2026Updated 3 weeks ago
- 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
- A library for activation patching based on nnsight.☆12May 27, 2025Updated last year
- Quantifying degeneracy in toy models☆11Sep 6, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆15Sep 21, 2022Updated 4 years ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated 2 years ago
- Erasing concepts from neural representations with provable guarantees☆271Jan 27, 2025Updated last year
- ☆29Feb 1, 2023Updated 3 years ago
- ☆26Jan 28, 2025Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆226Oct 26, 2026Updated last week
- Minimum Description Length probing for neural network representations☆20Jan 28, 2025Updated last year
- ☆13Apr 29, 2024Updated 2 years ago
- A benchmark for mechanistic discovery of circuits in Transformers☆18Dec 15, 2024Updated last year
- 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.
- official repository for the Instance Prototype Contrastive Learning (IPCL)☆18Jun 20, 2022Updated 4 years ago
- ☆58Jun 15, 2023Updated 3 years ago
- ☆29Feb 27, 2025Updated last year
- graphpatch is a library for activation patching on PyTorch neural network models.☆22Feb 11, 2025Updated last year
- Pile Deduplication Code☆18May 15, 2023Updated 3 years ago
- Tools for optimizing steering vectors in LLMs.☆22Apr 10, 2025Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆280Updated this week
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆156Mar 9, 2024Updated 2 years ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆24Oct 18, 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.
- Reproducing "Natural Emergent Misalignment from Reward Hacking" (MacDiarmid et al., Anthropic 2025) with open-source models. Includes rew…☆35Oct 5, 2026Updated 3 weeks ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆228Dec 22, 2021Updated 4 years ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆30Nov 20, 2024Updated last year
- LUCID: Attention with Preconditioned Representations - A novel attention mechanism for improved long-context retrieval in Transformers☆13May 29, 2026Updated 5 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆619Aug 7, 2025Updated last year
- LLM inference with HuggingFace (experimental)☆11Feb 6, 2025Updated last year
- My personal website and blog☆12Oct 25, 2026Updated last week
- Mechanistic Interpretability Visualizations using React☆372Apr 30, 2026Updated 6 months ago
- A replication of "Toy Models of Superposition," a groundbreaking machine learning research paper published by authors affiliated with Ant…☆10Dec 30, 2023Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Easy training for Sparse Linear Autoencoders (https://arxiv.org/abs/2309.08600) with data from TransformerLens models.☆12Nov 1, 2023Updated 3 years ago
- ☆16May 24, 2026Updated 5 months ago
- ☆12Sep 26, 2019Updated 7 years ago
- ☆34Oct 20, 2026Updated 2 weeks ago
- ☆32Aug 30, 2023Updated 3 years ago
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.☆31Jul 8, 2026Updated 3 months ago
- A longitudinal reliability benchmark foundation for agent lifespan engineering.☆16Jun 5, 2026Updated 4 months ago