jnward / monosemanticity-repro
☆22Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for monosemanticity-repro
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆113Updated 3 weeks ago
- A new benchmark for measuring LLM's capability to detect bugs in large codebase.☆27Updated 5 months ago
- code for training & evaluating Contextual Document Embedding models☆120Updated this week
- ☆102Updated 3 months ago
- Just a bunch of benchmark logs for different LLMs☆116Updated 3 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆204Updated 6 months ago
- Functional Benchmarks and the Reasoning Gap☆78Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆161Updated last month
- look how they massacred my boy☆58Updated last month
- ☆57Updated 11 months ago
- Graph-based method for end-to-end code completion with context awareness on repository☆47Updated 2 months ago
- ☆64Updated 6 months ago
- Simple examples using Argilla tools to build AI☆42Updated last week
- ☆48Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- Sparse autoencoders for Contra text embedding models☆24Updated 7 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆181Updated 5 months ago
- The first dense retrieval model that can be prompted like an LM☆63Updated 2 months ago
- ☆72Updated last year
- Evaluating LLMs with fewer examples☆135Updated 7 months ago
- ☆73Updated 11 months ago
- ☆113Updated 6 months ago
- Attribute (or cite) statements generated by LLMs back to in-context information.☆149Updated last month
- ☆37Updated this week
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆77Updated 8 months ago
- ☆104Updated 8 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆125Updated last month
- RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly sui…☆75Updated 2 months ago
- ☆109Updated last week