© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8520
    Prev
    Next
    INDEX
    Explanations

    key players and their statistics in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.28
    1:0.06
    2:0.06
    3:0.03
    4:0.03
    5:0.02
    6:0.10
    7:0.13
    8:0.02
    9:0.06
    10:0.11
    11:0.04
    Negative Logits
     Rubio
    -3.80
     Alger
    -3.65
     Copenhagen
    -3.47
     Kyr
    -3.41
     Denmark
    -3.29
     Uganda
    -3.26
     Christensen
    -3.24
     Danish
    -3.22
     Ib
    -3.21
     Bj
    -3.21
    POSITIVE LOGITS
     Colts
    8.27
     Colt
    6.93
     Indianapolis
    5.22
     Indy
    4.66
     Peyton
    4.56
     Luck
    4.13
     Manning
    3.99
    Indian
    3.96
     Titans
    3.75
    NFL
    3.68
    Activations Density 0.008%

    No Known Activations