vgel / repeng
A library for making RepE control vectors
☆481Updated last month
Related projects ⓘ
Alternatives and complementary repositories for repeng
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆203Updated 6 months ago
- Visualize the intermediate output of Mistral 7B☆313Updated 9 months ago
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆282Updated last month
- Extract full next-token probabilities via language model APIs☆229Updated 8 months ago
- ☆411Updated last year
- Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens☆333Updated 5 months ago
- Sparse autoencoders☆342Updated last week
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆221Updated 6 months ago
- ☆451Updated 3 weeks ago
- Automatically evaluate your LLMs in Google Colab☆559Updated 6 months ago
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆235Updated 2 weeks ago
- Stop messing around with finicky sampling parameters and just use DRµGS!☆318Updated 5 months ago
- Training Sparse Autoencoders on Language Models☆469Updated this week
- ☆470Updated 2 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆232Updated 5 months ago
- A benchmark for emotional intelligence in large language models☆197Updated 3 months ago
- awesome synthetic (text) datasets☆242Updated 3 weeks ago
- Exact structure out of any language model completion.☆502Updated last year
- smolLM with Entropix sampler on pytorch☆139Updated 2 weeks ago
- Long context evaluation for large language models☆190Updated this week
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆811Updated this week
- utilities for decoding deep representations (like sentence embeddings) back to text☆737Updated last month
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆408Updated 2 months ago
- A comprehensive deep dive into the world of tokens☆214Updated 4 months ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆221Updated 2 weeks ago
- Neural Search☆344Updated 5 months ago
- visualizing attention for LLM users☆163Updated last year
- A simple Python sandbox for helpful LLM data agents☆170Updated 5 months ago
- Toolkit for attaching, training, saving and loading of new heads for transformer models☆246Updated 2 weeks ago
- The repository for the code of the UltraFastBERT paper☆514Updated 7 months ago