EleutherAI / features-across-time

Related projects ⓘ

Alternatives and complementary repositories for features-across-time

• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆13Updated last week
• KaiNylund / lm-weights-encode-time
  ☆68Updated 2 months ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆53Updated 8 months ago
• EleutherAI / improved-t5
  Experiments for efforts to train a new and improved t5
  ☆76Updated 6 months ago
• EleutherAI / mdl
  Minimum Description Length probing for neural network representations
  ☆16Updated last week
• ExtensityAI / benchmark
  Evaluation of neuro-symbolic engines
  ☆33Updated 3 months ago
• google-research-datasets / QAmeleon
  QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…
  ☆34Updated last year
• dvruette / barrel-rec-pytorch
  ☆53Updated 9 months ago
• YuchenJin / llm.c
  LLM training in simple, raw C/CUDA
  ☆12Updated last month
• KhoomeiK / complexity-scaling
  gzip Predicts Data-dependent Scaling Laws
  ☆32Updated 5 months ago
• crowsonkb / LDLM
  Latent Diffusion Language Models
  ☆67Updated last year
• bilal-chughtai / rep-theory-mech-interp
  ☆24Updated last year
• allenai / EmbeddingRecycling
  Embedding Recycling for Language models
  ☆38Updated last year
• RobertCsordas / moeut
  ☆61Updated 2 months ago
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated 5 months ago
• epfml / schedules-and-scaling
  ☆50Updated last week
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆57Updated last year
• haileyschoelkopf / triton-index
  See https://github.com/cuda-mode/triton-index/ instead!
  ☆11Updated 6 months ago
• UKPLab / on-emergence
  Codes and files for the paper Are Emergent Abilities in Large Language Models just In-Context Learning
  ☆34Updated 7 months ago
• amudide / switch_sae
  Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)
  ☆13Updated 3 weeks ago
• epfml / DenseFormer
  ☆76Updated 6 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆60Updated last month
• shikaiqiu / compute-better-spent
  ☆46Updated last month
• Aleph-Alpha / trigrams
  ☆44Updated 2 months ago
• jbloomAus / SAEDashboard
  ☆18Updated 2 weeks ago
• ekinakyurek / google-research
  Google Research
  ☆45Updated 2 years ago
• NousResearch / StripedHyenaTrainer
  ☆55Updated 11 months ago
• callummcdougall / sae_visualizer
  ☆24Updated 7 months ago
• ltgoslo / bert-in-context
  Official implementation of "BERTs are Generative In-Context Learners"
  ☆19Updated 4 months ago
• kaiokendev / cutoff-len-is-context-len
  Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit
  ☆63Updated last year