VectorInstitute / vector-inference

Related projects ⓘ

Alternatives and complementary repositories for vector-inference

• VectorInstitute / vectorlm
  LLM finetuning in resource-constrained environments.
  ☆41Updated 4 months ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆53Updated 9 months ago
• google-research / jax-influence
  ☆59Updated 2 years ago
• KihoPark / linear_rep_geometry
  ☆75Updated 9 months ago
• pomonam / kronfluence
  Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
  ☆100Updated 3 months ago
• saprmarks / feature-circuits
  ☆102Updated last month
• epfml / llm-baselines
  NanoGPT-like codebase for LLM training
  ☆73Updated this week
• epfml / schedules-and-scaling
  ☆50Updated last week
• VectorInstitute / kaleidoscope
  A user toolkit for analyzing and interfacing with Large Language Models (LLMs)
  ☆21Updated 2 months ago
• saprmarks / geometry-of-truth
  ☆70Updated 3 months ago
• VectorInstitute / flex_model
  ☆12Updated 8 months ago
• EleutherAI / sae-auto-interp
  ☆105Updated this week
• neubig / research-career-tools
  ☆149Updated 6 months ago
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆95Updated 6 months ago
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆87Updated 5 months ago
• milesaturpin / cot-unfaithfulness
  ☆32Updated last year
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆83Updated 7 months ago
• shauli-ravfogel / rlace-icml
  ☆34Updated 2 years ago
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆228Updated 8 months ago
• young-geng / mlxu
  Machine Learning eXperiment Utilities
  ☆44Updated 5 months ago
• redwoodresearch / Easy-Transformer
  ☆96Updated 3 months ago
• google-deepmind / mishax
  ☆100Updated 3 months ago
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆50Updated 10 months ago
• EleutherAI / w2s
  ☆18Updated last month
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆26Updated 5 months ago
• guy-dar / embedding-space
  ☆50Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆186Updated last month
• microsoft / mechanistic-error-probe
  A mechanistic approach for understanding and detecting factual errors of large language models.
  ☆39Updated 4 months ago
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆62Updated last year
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆161Updated 6 months ago