© 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. 8873
    Prev
    Next
    INDEX
    Explanations

    instances of promotion or mention of celebrity teams or personas

    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
    0:0.10
    1:0.03
    2:0.07
    3:0.04
    4:0.03
    5:0.03
    6:0.28
    7:0.04
    8:0.04
    9:0.22
    10:0.03
    11:0.03
    Negative Logits
     Eag
    -4.27
    oros
    -4.15
    Oracle
    -3.85
    ajor
    -3.78
     Ellison
    -3.77
    alore
    -3.70
     Hobby
    -3.68
    aga
    -3.59
    orus
    -3.57
     Orion
    -3.55
    POSITIVE LOGITS
    Sm
    8.69
     Sm
    8.66
    sm
    7.74
     sm
    7.70
     Smoking
    6.29
     Smoke
    6.17
     smoker
    6.01
    SM
    5.72
     smoked
    5.60
     SM
    5.44
    Activations Density 0.003%

    No Known Activations