Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"
☆17Mar 31, 2025Updated last year
Alternatives and similar repositories for LoRA-Models-for-SAEs
Users that are interested in LoRA-Models-for-SAEs are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for the paper "Distinguishing the Knowable from the Unknowable with Language Models"☆11Jul 18, 2026Updated 3 weeks ago
- DESSERT Effeciently Searches Sets of Embeddings via Retrieval Tables☆18Feb 21, 2024Updated 2 years ago
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated last year
- code for EMNLP 2024 paper: Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis☆12Nov 17, 2024Updated last year
- small language models training made easy☆17Dec 15, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year
- ☆182May 1, 2026Updated 3 months ago
- On-the-fly Definition Augmentation of LLMs for Biomedical NER☆14Apr 14, 2025Updated last year
- Few-Shot Preference Optimization (FSPO) personalizes LLMs by reframing reward modeling as a meta-learning problem, enabling rapid adaptat…☆16Feb 27, 2025Updated last year
- Modified to support crosscoder training.☆27Jul 2, 2026Updated last month
- ☆38Feb 20, 2025Updated last year
- How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients☆20Jun 17, 2025Updated last year
- Sparsify transformers with SAEs and transcoders☆734Updated this week
- ☆19Oct 14, 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.
- ☆18Jan 9, 2025Updated last year
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆18Mar 15, 2024Updated 2 years ago
- ☆15Apr 14, 2025Updated last year
- Implementation of "Analysing Mathematical Reasoning Abilities of Neural Models"☆30Mar 25, 2023Updated 3 years ago
- ☆17Jun 17, 2025Updated last year
- Control LLM generation format efficiently. A simple version of microsoft/aici in vllm and transformers☆14Jun 7, 2024Updated 2 years ago
- code for EMNLP 2024 paper: How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for M…☆13Nov 17, 2024Updated last year
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- ☆18Jun 19, 2023Updated 3 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Code to produce syntactic representations that can be used to study syntax processing in the human brain☆12Nov 22, 2021Updated 4 years ago
- Code for 'The Geometry of Categorical and Hierarchical Concepts in Large Language Models' (ICLR 2025, Oral)☆116Feb 11, 2025Updated last year
- ☆10Mar 4, 2024Updated 2 years ago
- ☆224Oct 14, 2025Updated 10 months ago
- [EMNLP 2024 Findings] ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs☆29May 22, 2025Updated last year
- ☆17Nov 10, 2021Updated 4 years ago
- ☆13Apr 17, 2018Updated 8 years ago
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆30Oct 14, 2025Updated 10 months ago
- [EMNLP 2024] Tree of Problems: Improving structured problem solving with compositionality☆20Mar 4, 2025Updated last year
- 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.
- CUDA implementation of Multidimensional Scaling☆15May 8, 2021Updated 5 years ago
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆12Jun 18, 2024Updated 2 years ago
- Use Retro Diffusion's API to create tilesets from two textures☆22Apr 7, 2025Updated last year
- Contains the code for my Imperial College London Master's thesis on text summarization☆11Oct 25, 2022Updated 3 years ago
- A python implementation of PROCLUS: PROjected CLUStering algorithm.☆10Jan 12, 2015Updated 11 years ago
- ☆429Aug 21, 2025Updated 11 months ago
- ACL 2023 *oral* paper "MGR: Multi-generator based Rationalization"☆10Nov 21, 2024Updated last year