Companion code for the global workspace interpretability paper
☆2,002Sep 19, 2026Updated 2 weeks ago
Alternatives and similar repositories for jacobian-lens
Users that are interested in jacobian-lens are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- open source interpretability platform 🧠☆1,152Updated this week
- ☆954Aug 2, 2026Updated 2 months ago
- Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.☆230Sep 6, 2026Updated 3 weeks ago
- ☆2,913Sep 20, 2026Updated last week
- The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away fro…☆175Jan 20, 2026Updated 8 months ago
- 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.
- Preregistered Jacobian-lens reliability research on Gemma 4: 25k prompts, frozen probes, public traces, a prospective transfer miss, and …☆54Sep 11, 2026Updated 3 weeks ago
- A library for mechanistic interpretability of GPT-style language models☆3,931Updated this week
- To know what models don't say out loud.☆244Jul 23, 2026Updated 2 months ago
- Repository for "Training Language Models To Explain Their Own Computations"☆38Jul 7, 2026Updated 2 months ago
- ADAG: Transluce's MLP neuron-level circuit tracing library☆39Apr 10, 2026Updated 5 months ago
- Head Vis Public Release☆41May 4, 2026Updated 4 months ago
- AI agents running research on single-GPU nanochat training automatically☆97,133Mar 26, 2026Updated 6 months ago
- Agentic RL Training at Scale☆2,102Updated this week
- The best ChatGPT that $100 can buy.☆58,383Sep 7, 2026Updated 3 weeks ago
- 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.
- Train Embedding Models on MLX.☆17Jun 2, 2026Updated 4 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,117Updated this week
- Renderer for the harmony response format to be used with gpt-oss☆4,513Apr 8, 2026Updated 5 months ago
- ☆103Sep 26, 2026Updated last week
- Interactive Jacobian-Lens visualizer and live steerer for GGUF models on llama.cpp☆87Jul 12, 2026Updated 2 months ago
- ☆6,560Apr 1, 2026Updated 6 months ago
- NanoGPT (124M) in 90 seconds☆5,895Updated this week
- Training LLMs to Report Their Learned Behaviors☆30Apr 28, 2026Updated 5 months ago
- Decomposing and measuring evaluation awareness in existing benchmarks and our proposed EvalAwareBench.☆20Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.☆77,128Updated this week
- dLLM: Simple Diffusion Language Modeling☆2,699Jul 17, 2026Updated 2 months ago
- AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI☆111,674Updated this week
- Open-source cross-modal and multimodal prompt injection test suite. 250,000+ attack payloads across text, image, document, and audio moda…☆76Jul 22, 2026Updated 2 months ago
- ICA Lens: compact ICA-based interpretability tools for exploring LLM activations. Code release for the paper.☆45Updated this week
- ☆18Sep 18, 2026Updated 2 weeks ago
- Code for COLM '26 paper 'Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers'☆101Sep 3, 2026Updated last month
- slime is an LLM post-training framework for RL Scaling.☆8,586Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,719Updated this week
- 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.
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,182Jul 9, 2026Updated 2 months ago
- Make abliterated models with transformers, easy and fast☆194Mar 24, 2026Updated 6 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆93,064Updated this week
- Train the smallest LM you can that fits in 16MB. Best model wins!☆5,198Updated this week
- Tools for merging pretrained large language models.☆7,385Sep 12, 2026Updated 3 weeks ago
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆465Apr 22, 2026Updated 5 months ago
- Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.☆130Updated this week