Alternatives and similar repositories for attention-viz

Users that are interested in attention-viz are comparing it to the libraries listed below

• wesg52 / world-models
  Extracting spatial and temporal world models from LLMs
  ☆257Updated 2 years ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆191Updated 2 years ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆193Updated last year
• google-deepmind / mishax
  ☆142Updated 2 months ago
• HazyResearch / TART
  TART: A plug-and-play Transformer module for task-agnostic reasoning
  ☆200Updated 2 years ago
• llm-merging / LLM-Merging
  LLM-Merging: Building LLMs Efficiently through Merging
  ☆204Updated last year
• lukasberglund / reversal_curse
  ☆297Updated last year
• KaiNylund / lm-weights-encode-time
  ☆69Updated last year
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆111Updated 8 months ago
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆536Updated 3 months ago
• srush / do-we-need-attention
  ☆166Updated 2 years ago
• SALT-NLP / demonstrated-feedback
  ☆129Updated last year
• allenai / fm-cheatsheet
  Website for hosting the Open Foundation Models Cheat Sheet.
  ☆267Updated 6 months ago
• huggingface / datablations
  Scaling Data-Constrained Language Models
  ☆342Updated 4 months ago
• OSU-NLP-Group / GrokkedTransformer
  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
  ☆232Updated 3 months ago
• facebookresearch / Shepherd
  This is the repo for the paper Shepherd -- A Critic for Language Model Generation
  ☆217Updated 2 years ago
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆89Updated last year
• Zyphra / BlackMamba
  Code repository for Black Mamba
  ☆258Updated last year
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆129Updated 3 years ago
• lucidrains / CALM-pytorch
  Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind
  ☆177Updated last year
• booydar / LM-RMT
  Recurrent Memory Transformer
  ☆151Updated 2 years ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆221Updated last week
• lucidrains / llama-qrlhf
  Implementation of the Llama architecture with RLHF + Q-learning
  ☆167Updated 9 months ago
• felipemaiapolo / tinyBenchmarks
  Evaluating LLMs with fewer examples
  ☆165Updated last year
• neulab / gemini-benchmark
  ☆149Updated last year
• joshuacnf / Ctrl-G
  ☆103Updated 10 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆83Updated 11 months ago
• lz1oceani / verify_cot
  ☆134Updated 2 years ago
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆100Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆224Updated 10 months ago