msakarvadia / AttentionLens

Related projects ⓘ

Alternatives and complementary repositories for AttentionLens

• AndyShih12 / LongHorizonTemperatureScaling
  PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023
  ☆19Updated last year
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆16Updated 3 weeks ago
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆44Updated last year
• bilal-chughtai / rep-theory-mech-interp
  ☆26Updated last year
• nrimsky / InfluenceFunctions
  Implementation of Influence Function approximations for differently sized ML models, using PyTorch
  ☆15Updated last year
• epfml / schedules-and-scaling
  ☆53Updated 3 weeks ago
• XiangLi1999 / AutoBencher
  ☆24Updated 4 months ago
• google / belief-localization
  This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…
  ☆55Updated last year
• milesaturpin / cot-unfaithfulness
  ☆32Updated last year
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆25Updated 5 months ago
• petezh / OpenD5
  Tasks for describing differences between text distributions.
  ☆16Updated 3 months ago
• vedantpalit / Towards-Vision-Language-Mechanistic-Interpretability
  This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…
  ☆17Updated 7 months ago
• jmerullo / lm_vector_arithmetic
  ☆28Updated last year
• IBM / ColPret
  Efficient Scaling laws and collaborative pretraining.
  ☆13Updated this week
• scalable-model-editing / unified-model-editing
  We introduce EMMET and unify model editing with popular algorithms ROME and MEMIT.
  ☆12Updated 2 months ago
• Ping-C / optimizer
  This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…
  ☆34Updated last year
• zeyuyun1 / TransformerVis
  ☆35Updated 3 years ago
• srush / mamba-scans
  Blog post
  ☆16Updated 9 months ago
• shikaiqiu / compute-better-spent
  ☆46Updated last month
• bergen / EdgeTransformer
  ☆21Updated 2 years ago
• activatedgeek / calibration-tuning
  ☆36Updated 3 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆31Updated last month
• hartvigsen-group / composable-interventions
  ☆21Updated this week
• jbloomAus / SAEDashboard
  ☆20Updated last week
• berlino / seq_icl
  ☆50Updated 6 months ago
• guy-dar / embedding-space
  ☆50Updated last year
• EleutherAI / mdl
  Minimum Description Length probing for neural network representations
  ☆16Updated last week
• felixzli / synthetic_pretraining
  ☆40Updated 2 years ago
• r-three / RAD
  Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
  ☆41Updated 10 months ago
• sustcsonglin / mamba-triton
  ☆45Updated 9 months ago