© 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. 9-ATT-KK
    11. 1180
    Prev
    Next
    INDEX
    Explanations

    references to college sports teams and notable athletes

    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
    0:0.04
    1:0.03
    2:0.05
    3:0.08
    4:0.05
    5:0.05
    6:0.07
    7:0.06
    8:0.38
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
     Dominican
    -4.30
    atari
    -3.83
     Blasio
    -3.82
     Chavez
    -3.61
     Cuban
    -3.61
    Cub
    -3.54
    icio
    -3.46
    uy
    -3.42
     Latino
    -3.36
     Maduro
    -3.32
    POSITIVE LOGITS
     Canberra
    5.62
     Adelaide
    5.22
     Queensland
    5.02
     NSW
    4.90
     Perth
    4.83
     Brisbane
    4.72
     NRL
    4.61
     Tasman
    4.45
     NBN
    4.44
     Tasmania
    4.43
    Activations Density 0.007%

    No Known Activations