Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

BurnyCoder
/
grokking-modular-addition-runs

grokking
mechanistic-interpretability
modular-arithmetic
transformer
Model card Files Files and versions
xet
Community
grokking-modular-addition-runs
9.06 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 4 commits
BurnyCoder's picture
BurnyCoder
Model card: 19 runs on (a + b) mod 113 and 3 random-label controls; float64 loss
98c61de verified 1 day ago
  • rand_s0
    Upload runs 5 days ago
  • rand_s1
    Upload runs 5 days ago
  • rand_s2
    Upload runs 5 days ago
  • split0_init100
    Upload runs 5 days ago
  • split0_init101
    Upload runs 5 days ago
  • split0_init102
    Upload runs 5 days ago
  • wd0_s0
    Upload runs 5 days ago
  • wd0_s1
    Upload runs 5 days ago
  • wd0_s2
    Upload runs 5 days ago
  • wd0_s3
    Upload runs 5 days ago
  • wd0_s4
    Upload runs 5 days ago
  • wd1_s0
    Upload runs 5 days ago
  • wd1_s1
    Upload runs 5 days ago
  • wd1_s10
    Upload runs 5 days ago
  • wd1_s2
    Upload runs 5 days ago
  • wd1_s3
    Upload runs 5 days ago
  • wd1_s4
    Upload runs 5 days ago
  • wd1_s5
    Upload runs 5 days ago
  • wd1_s6
    Upload runs 5 days ago
  • wd1_s7
    Upload runs 5 days ago
  • wd1_s8
    Upload runs 5 days ago
  • wd1_s9
    Upload runs 5 days ago
  • .gitattributes
    1.52 kB
    initial commit 5 days ago
  • README.md
    2.95 kB
    Model card: 19 runs on (a + b) mod 113 and 3 random-label controls; float64 loss 1 day ago