Official Repository of Paper "Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs"
☆15Sep 25, 2025Updated 10 months ago
Alternatives and similar repositories for WeightWatch
Users that are interested in WeightWatch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆15Sep 29, 2022Updated 3 years ago
- ☆26Feb 20, 2026Updated 5 months ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆19May 19, 2019Updated 7 years ago
- 6,080-param transformer achieving 100% accuracy on 10-digit addition. Trained from scratch in 10 minutes.☆22Feb 19, 2026Updated 5 months ago
- Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"☆34Mar 31, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆20Mar 22, 2026Updated 4 months ago
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆30Oct 14, 2025Updated 9 months ago
- Implementing scalable LLMs in pure JAX (no third-party libraries)☆54Jun 11, 2026Updated last month
- ☆36Jul 5, 2023Updated 3 years ago
- Flax (JAX) implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation☆12May 24, 2021Updated 5 years ago
- Global CoT Analysis: Initial attempts to uncover patterns across many chains of thought☆20Feb 10, 2026Updated 5 months ago
- A framework to meta-train transformers for causal ICL☆11Jul 15, 2026Updated 3 weeks ago
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆35Oct 28, 2025Updated 9 months ago
- Subliminal learning in LLMs: language models can transmit hidden preferences through seemingly unrelated training data.☆25Nov 9, 2025Updated 9 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Composite Backdoor Attacks Against Large Language Models☆25Apr 12, 2024Updated 2 years ago
- [ICLR2026] Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models☆28Apr 19, 2026Updated 3 months ago
- ☆15Apr 15, 2026Updated 3 months ago
- ☆22Jun 2, 2026Updated 2 months ago
- ☆40Jul 9, 2025Updated last year
- All my experiments with the various transformers and various transformer frameworks available☆14Apr 30, 2021Updated 5 years ago
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation☆83May 2, 2025Updated last year
- The 4th rank system of the SemEval 2021 Task4.☆10May 7, 2022Updated 4 years ago
- Curated list of Moroccans publishing in the most prestigious AI conferences☆11Jul 6, 2026Updated last month
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Code for the paper "Distinguishing the Knowable from the Unknowable with Language Models"☆11Jul 18, 2026Updated 3 weeks ago
- FROM $f(x)$ AND $g(x)$ TO $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones☆71Jan 26, 2026Updated 6 months ago
- Implemented a two-level (L1 and L2) cache simulator in C++ with round robin eviction policy☆10Jan 4, 2017Updated 9 years ago
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆37Jun 1, 2025Updated last year
- The complete [1 to 5]-gram Gumar Corpus in the style of Google n-grams.☆12Feb 5, 2020Updated 6 years ago
- ☆36Jun 13, 2025Updated last year
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆11Dec 30, 2024Updated last year
- Official PyTorch Implementation for Learning a Generative Meta-Model of LLM Activations, ICML 2026☆91Apr 30, 2026Updated 3 months ago
- ☆18Mar 3, 2026Updated 5 months ago
- 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.
- Code for AttriBoT from "AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution"☆15Apr 21, 2025Updated last year
- Pytorch routines for (Ker)nel (Mac)hines☆12Oct 10, 2025Updated 9 months ago
- ☆10Nov 6, 2024Updated last year
- ☆10Jul 21, 2023Updated 3 years ago
- Official repository for Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning☆12Sep 2, 2024Updated last year
- Arabic News☆12Dec 16, 2021Updated 4 years ago
- Tunisian Arabish Corpus☆12Mar 12, 2024Updated 2 years ago