© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6328
    Prev
    Next
    INDEX
    Explanations

    references to childbirth and babies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.05
    1:0.03
    2:0.12
    3:0.04
    4:0.07
    5:0.05
    6:0.31
    7:0.06
    8:0.03
    9:0.11
    10:0.03
    11:0.04
    Negative Logits
     Trails
    -3.98
    Rog
    -3.81
     Rog
    -3.67
     Wilkinson
    -3.60
     Magnet
    -3.25
     Vil
    -3.23
     Sorce
    -3.22
     Nord
    -3.21
     Mus
    -3.20
     Zin
    -3.18
    POSITIVE LOGITS
    Baby
    8.62
     Baby
    8.54
     baby
    8.51
    baby
    8.36
     babies
    7.47
     infant
    6.87
     newborn
    6.42
     infants
    5.92
     Bab
    5.83
     fetal
    5.74
    Activations Density 0.022%

    No Known Activations