Official Code for What Makes and Breaks Safety Fine-tuning? A Mechanistic Study (NeurIPS 2024)
☆12Oct 31, 2024Updated last year
Alternatives and similar repositories for understanding_safety_finetuning
Users that are interested in understanding_safety_finetuning are comparing it to the libraries listed below
Sorting:
- ☆15Aug 19, 2025Updated 6 months ago
- ☆15Mar 13, 2025Updated 11 months ago
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated last year
- Tools for optimizing steering vectors in LLMs.☆20Apr 10, 2025Updated 10 months ago
- A tiny easily hackable implementation of a feature dashboard.☆15Oct 21, 2025Updated 4 months ago
- [CVPR-2023] Official Code for DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks☆12May 30, 2023Updated 2 years ago
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆19Dec 14, 2024Updated last year
- ☆17Feb 25, 2026Updated last week
- ☆17Nov 7, 2023Updated 2 years ago
- Erasing conceptual knowledge from language models through low-rank fine-tuning☆19Mar 27, 2025Updated 11 months ago
- [NeurIPS 2024] VeLoRA : Memory Efficient Training using Rank-1 Sub-Token Projections☆21Oct 15, 2024Updated last year
- Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"☆27Jun 4, 2024Updated last year
- ☆25Feb 20, 2026Updated last week
- ☆30Aug 2, 2024Updated last year
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆29Feb 6, 2026Updated 3 weeks ago
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆75Jun 23, 2025Updated 8 months ago
- ☆13Oct 5, 2025Updated 5 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆34Mar 8, 2025Updated 11 months ago
- ☆11Jun 20, 2023Updated 2 years ago
- Build an AI bot in Discord to serve user's personalized reports on what's up in tech☆28Sep 14, 2025Updated 5 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆47May 31, 2024Updated last year
- CLI app to automate assignment of on-call shifts via constraint solving by use of the OR-tools library.☆11Mar 12, 2023Updated 2 years ago
- Linear Relational Embeddings (LREs) and Linear Relational Concepts (LRCs) for LLMs in PyTorch☆10Aug 7, 2024Updated last year
- Reference implementation of Thin and Deep Gaussian Processes (NeurIPS 2023)☆14Nov 25, 2024Updated last year
- Trains small LMs. Designed for training on SimpleStories☆12Sep 15, 2025Updated 5 months ago
- ☆10Oct 29, 2020Updated 5 years ago
- Code for experiments on self-prediction as a way to measure introspection in LLMs☆16Dec 10, 2024Updated last year
- ☆12Jul 8, 2024Updated last year
- my profile readme☆14Updated this week
- ☆12Jun 26, 2024Updated last year
- cron parser/generator☆12Jan 6, 2023Updated 3 years ago
- ☆31Feb 3, 2026Updated last month
- Official implementation of "Interpreting and Controlling Vision Foundation Models via Text Explanations"☆14May 29, 2024Updated last year
- 6,080-param transformer achieving 100% accuracy on 10-digit addition. Trained from scratch in 10 minutes.☆21Feb 19, 2026Updated 2 weeks ago
- Code for "What really matters in matrix-whitening optimizers?"☆22Oct 31, 2025Updated 4 months ago
- Minimal Transformer base in JAX. A single backbone for language modelling, diffusion, classification, etc...☆14May 28, 2025Updated 9 months ago
- Unofficial implementation of "Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle"☆13Jul 3, 2024Updated last year
- ☆14Mar 15, 2025Updated 11 months ago