Alternatives and similar repositories for monosemanticity-repro:

Users that are interested in monosemanticity-repro are comparing it to the libraries listed below

• Mihaiii / llm_steer
  Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…
  ☆222Updated this week
• teknium1 / transformers-gptq-quant
  ☆48Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆182Updated 2 months ago
• wolfecameron / lora_instruction_tune
  ☆40Updated 9 months ago
• joshuacnf / Ctrl-G
  ☆80Updated last month
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆82Updated 4 months ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆185Updated 8 months ago
• emrgnt-cmplxty / zero-shot-replication
  ☆74Updated last year
• google-deepmind / mishax
  ☆121Updated last week
• teknium1 / LLM-Benchmark-Logs
  Just a bunch of benchmark logs for different LLMs
  ☆119Updated 6 months ago
• patronus-ai / Lynx-hallucination-detection
  ☆32Updated 7 months ago
• 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…
  ☆85Updated 5 months ago
• geronimi73 / qlora-minimal
  ☆82Updated last year
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆167Updated last month
• automix-llm / automix
  Mixing Language Models with Self-Verification and Meta-Verification
  ☆100Updated 2 months ago
• cognitivecomputations / spectrum
  ☆113Updated 4 months ago
• Mihaiii / backtrack_sampler
  An easy-to-understand framework for LLM samplers that rewind and revise generated tokens
  ☆130Updated this week
• shengliu66 / ICV
  Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
  ☆162Updated last week
• akjindal53244 / Arithmo
  Small and Efficient Mathematical Reasoning LLMs
  ☆71Updated last year
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆185Updated 4 months ago
• sdan / selfextend
  an implementation of Self-Extend, to expand the context window via grouped attention
  ☆118Updated last year
• thesephist / spectre
  Sparse autoencoders for Contra text embedding models
  ☆25Updated 9 months ago
• jongjyh / TrFr
  Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
  ☆45Updated last year
• AblateIt / finetune-study
  Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.
  ☆82Updated last year
• leehanchung / lora-instruct
  Finetune Falcon, LLaMA, MPT, and RedPajama on consumer hardware using PEFT LoRA
  ☆101Updated 6 months ago
• NousResearch / StripedHyenaTrainer
  ☆60Updated last year
• felipemaiapolo / tinyBenchmarks
  Evaluating LLMs with fewer examples
  ☆145Updated 10 months ago
• Pleias / Various-Finetuning
  Set of scripts to finetune LLMs
  ☆36Updated 10 months ago