© 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. 5630
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to numbers and quantities

    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
    0:0.09
    1:0.03
    2:0.09
    3:0.04
    4:0.04
    5:0.03
    6:0.23
    7:0.03
    8:0.03
    9:0.29
    10:0.03
    11:0.02
    Negative Logits
     Realm
    -3.92
     mysql
    -3.74
     Stanton
    -3.63
    erva
    -3.59
    enger
    -3.54
     Kart
    -3.52
     Trafford
    -3.51
    AMS
    -3.47
     Pegasus
    -3.47
     ammon
    -3.47
    POSITIVE LOGITS
    Cut
    7.57
     Cut
    7.46
     cut
    6.62
     Cutting
    6.48
    cut
    6.45
     cuts
    6.28
     cutting
    6.26
    cutting
    6.24
     chop
    6.10
    cuts
    6.02
    Activations Density 0.014%

    No Known Activations