Understanding how features learned by neural networks evolve throughout training
☆41Oct 24, 2024Updated last year
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…☆29May 23, 2024Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Jun 19, 2024Updated last year
- Erasing concepts from neural representations with provable guarantees☆246Jan 27, 2025Updated last year
- ☆15Sep 21, 2022Updated 3 years ago
- ☆24Jan 28, 2025Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- ☆11Aug 13, 2025Updated 8 months ago
- ☆27Feb 1, 2023Updated 3 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆217Apr 6, 2026Updated last week
- What you really need to know about Vim motions when starting to learn them.☆20Jul 31, 2024Updated last year
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year
- ☆58Jun 15, 2023Updated 2 years ago
- Redwood Research's transformer interpretability tools☆15Apr 15, 2022Updated 3 years ago
- Hide text informations using invisible text characters☆12Apr 4, 2022Updated 4 years ago
- Minimum Description Length probing for neural network representations☆20Jan 28, 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 and start building anything your business needs.
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆104Dec 22, 2024Updated last year
- ☆23Oct 4, 2024Updated last year
- Pile Deduplication Code☆18May 15, 2023Updated 2 years ago
- A toy Inspect implementation of the Bliss Attractor eval from Claude 4 System Card Welfare Assessment☆38Jun 5, 2025Updated 10 months ago
- ☆19Nov 4, 2025Updated 5 months ago
- ☆103Jan 24, 2026Updated 2 months ago
- [NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in La…☆27Nov 3, 2025Updated 5 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆22Oct 18, 2024Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆214Dec 22, 2021Updated 4 years ago
- Code for our paper "Fixed-point Inversion for Text-to-image diffusion models"☆19Oct 13, 2024Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆580Aug 7, 2025Updated 8 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆248Apr 6, 2026Updated last week
- Layerwise Batch Entropy Regularization☆24Aug 3, 2022Updated 3 years ago
- ☆24Oct 25, 2024Updated last year
- Official Implementation of "RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs"☆28Jul 23, 2025Updated 8 months ago
- Mapping out the "memory" of neural nets with data attribution☆52Updated this week
- ☆12Sep 26, 2019Updated 6 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Efficiently computing & storing token n-grams from large corpora☆27Oct 6, 2024Updated last year
- ☆159Dec 30, 2025Updated 3 months ago
- ☆11Nov 27, 2019Updated 6 years ago
- ☆10Dec 8, 2017Updated 8 years ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆141Mar 9, 2024Updated 2 years ago
- ☆14Mar 15, 2025Updated last year
- ☆11Sep 10, 2023Updated 2 years ago