jnward / monosemanticity-repro

Related projects ⓘ

Alternatives and complementary repositories for monosemanticity-repro

• Mihaiii / backtrack_sampler
  An easy-to-understand framework for LLM samplers that rewind and revise generated tokens
  ☆113Updated 3 weeks ago
• HammingHQ / bug-in-the-code-stack
  A new benchmark for measuring LLM's capability to detect bugs in large codebase.
  ☆27Updated 5 months ago
• jxmorris12 / cde
  code for training & evaluating Contextual Document Embedding models
  ☆120Updated this week
• google-deepmind / mishax
  ☆102Updated 3 months ago
• teknium1 / LLM-Benchmark-Logs
  Just a bunch of benchmark logs for different LLMs
  ☆116Updated 3 months ago
• Mihaiii / llm_steer
  Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…
  ☆204Updated 6 months ago
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆78Updated last month
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆161Updated last month
• xjdr-alt / llmri
  look how they massacred my boy
  ☆58Updated last month
• NousResearch / StripedHyenaTrainer
  ☆57Updated 11 months ago
• FSoft-AI4Code / RepoHyper
  Graph-based method for end-to-end code completion with context awareness on repository
  ☆47Updated 2 months ago
• cognitivecomputations / kraken
  ☆64Updated 6 months ago
• argilla-io / argilla-cookbook
  Simple examples using Argilla tools to build AI
  ☆42Updated last week
• teknium1 / transformers-gptq-quant
  ☆48Updated last year
• AblateIt / finetune-study
  Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.
  ☆81Updated last year
• thesephist / spectre
  Sparse autoencoders for Contra text embedding models
  ☆24Updated 7 months ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆181Updated 5 months ago
• orionw / promptriever
  The first dense retrieval model that can be prompted like an LM
  ☆63Updated 2 months ago
• emrgnt-cmplxty / zero-shot-replication
  ☆72Updated last year
• felipemaiapolo / tinyBenchmarks
  Evaluating LLMs with fewer examples
  ☆135Updated 7 months ago
• swj0419 / detect-pretrain-code-contamination
  ☆73Updated 11 months ago
• NousResearch / finetuning-subnet
  ☆113Updated 6 months ago
• MadryLab / context-cite
  Attribute (or cite) statements generated by LLMs back to in-context information.
  ☆149Updated last month
• yueqis / API-Based-Agent
  ☆37Updated this week
• Hannibal046 / nanoColBERT
  Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).
  ☆77Updated 8 months ago
• teknium1 / ShareGPT-Builder
  ☆104Updated 8 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆125Updated last month
• lumpenspace / raft
  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
• EleutherAI / sae-auto-interp
  ☆109Updated last week