© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 22121
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their roles or actions in specific contexts

    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
    0:0.17
    1:0.22
    2:0.03
    3:0.03
    4:0.02
    5:0.02
    6:0.13
    7:0.09
    8:0.06
    9:0.02
    10:0.10
    11:0.05
    Negative Logits
     LGBT
    -2.92
     Creed
    -2.78
     Vendor
    -2.66
    ay
    -2.61
    pole
    -2.57
     ACS
    -2.55
     Aki
    -2.51
     gay
    -2.49
     Capcom
    -2.48
     Chinatown
    -2.42
    POSITIVE LOGITS
    ran
    3.61
    rit
    3.38
     roy
    2.94
    nder
    2.93
     Imran
    2.81
    raf
    2.74
    raz
    2.74
    runs
    2.73
     Gry
    2.67
     PT
    2.65
    Activations Density 0.002%

    No Known Activations