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

    Neuronpedia

    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. 9-ATT-KK
    11. 11053
    Prev
    Next
    INDEX
    Explanations

    events or actions related to sports, particularly concerning player dynamics and coaching decisions

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

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.07
    3:0.03
    4:0.06
    5:0.03
    6:0.25
    7:0.06
    8:0.07
    9:0.20
    10:0.02
    11:0.04
    Negative Logits
     indu
    -3.91
     acet
    -3.57
     techno
    -3.56
    beit
    -3.55
     Tud
    -3.48
     methyl
    -3.48
     colonies
    -3.26
     Sod
    -3.24
    acht
    -3.19
     colony
    -3.14
    POSITIVE LOGITS
     Griffin
    11.73
    Gr
    6.85
     Griff
    6.65
     RG
    6.43
     Grayson
    5.59
     Starr
    5.15
    RG
    5.04
     Redskins
    4.96
     Shanahan
    4.96
     Morrison
    4.94
    Activations Density 0.008%

    No Known Activations