© 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. 10-ATT-KK
    11. 6721
    Prev
    Next
    INDEX
    Explanations

    cooking and preparation times in recipes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.09
    1:0.03
    2:0.08
    3:0.05
    4:0.08
    5:0.15
    6:0.04
    7:0.16
    8:0.09
    9:0.11
    10:0.04
    11:0.03
    Negative Logits
    soDeliveryDate
    -2.75
     [&
    -2.75
    ."[
    -2.74
    …."
    -2.66
    forth
    -2.41
    "[
    -2.34
    .")
    -2.34
     aborted
    -2.31
     Mehran
    -2.25
    "/>
    -2.17
    POSITIVE LOGITS
     Dimensions
    2.56
     Amount
    2.54
     Ethnic
    2.51
     Cu
    2.50
     Vegan
    2.40
     Eating
    2.31
    rees
    2.27
     Container
    2.26
     Healthy
    2.24
     Serv
    2.23
    Activations Density 0.003%

    No Known Activations