Minimum Description Length probing for neural network representations
☆20Jan 28, 2025Updated last year
Alternatives and similar repositories for mdl
Users that are interested in mdl are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Easy training for Sparse Linear Autoencoders (https://arxiv.org/abs/2309.08600) with data from TransformerLens models.☆12Nov 1, 2023Updated 2 years ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation [ACL 2023]☆14Jul 11, 2023Updated 3 years ago
- Utilities for PyTorch distributed☆26Feb 27, 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.
- Mamba support for transformer lens☆20Sep 17, 2024Updated 2 years ago
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated last year
- Debate interface, experiments, etc.☆12Mar 12, 2024Updated 2 years ago
- Tools for exploring Transformer neuron behaviour, including input pruning and diversification.☆11Jun 6, 2023Updated 3 years ago
- Efficient Symptom Inquiring and Diagnosis via Adaptive Alignment of Reinforcement Learning and Classification [AI in Medicine Journal]☆14May 20, 2022Updated 4 years ago
- 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
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆33May 25, 2024Updated 2 years ago
- ☆26May 30, 2023Updated 3 years ago
- Biomedical Entity Linking Benchmark☆15Sep 24, 2026Updated last month
- 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.
- A benchmark for mechanistic discovery of circuits in Transformers☆18Dec 15, 2024Updated last year
- ☆21May 22, 2023Updated 3 years ago
- ☆17Feb 14, 2024Updated 2 years ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆57Nov 30, 2024Updated last year
- Sparse Autoencoder Training Library☆59May 1, 2025Updated last year
- 🤖ConvRe🤯: An Investigation of LLMs’ Inefficacy in Understanding Converse Relations (EMNLP 2023)☆24Oct 10, 2023Updated 3 years ago
- Benchmark evaluating LLMs on their ability to create and resist disinformation. Includes comprehensive testing across major models (Claud…☆36Mar 20, 2025Updated last year
- Engine for collecting, uploading, and downloading model activations☆31Apr 2, 2025Updated last year
- ☆50Mar 14, 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.
- Fast, High-Fidelity LLM Decoding with Regex Constraints☆21Jul 26, 2024Updated 2 years ago
- [NeurIPS 2025] RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models☆12Oct 6, 2026Updated 3 weeks ago
- Scripts and config files for SLURM☆13Sep 12, 2025Updated last year
- ☆28Feb 20, 2026Updated 8 months ago
- Erasing concepts from neural representations with provable guarantees☆270Jan 27, 2025Updated last year
- A Hub for Managing PyTorch Ambassador Program☆11Oct 22, 2026Updated last week
- ☆25Jun 30, 2025Updated last year
- Reasoning-based Evaluation and Ranking of Translations.☆23Jun 2, 2026Updated 4 months ago
- Calculating Expected Time for training LLM.☆39Apr 17, 2023Updated 3 years 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.
- Conic10K: A large-scale dataset for closed-vocabulary math problem understanding. Accepted to EMNLP2023 Findings.☆34Dec 6, 2023Updated 2 years ago
- ☆12Aug 26, 2025Updated last year
- [EMNLP 2022] Summarization as Indirect Supervision for Relation Extraction (SuRE)☆27Nov 22, 2022Updated 3 years ago
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- Official Code Repository for the paper "KALA: Knowledge-Augmented Language Model Adaptation" (NAACL 2022)☆35Oct 17, 2023Updated 3 years ago
- Transductive Active Learning with Application to Safe Bayesian Optimization☆11Mar 5, 2025Updated last year
- SAT Competition 2024☆11Aug 28, 2024Updated 2 years ago