© 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. 9-ATT-KK
    11. 14374
    Prev
    Next
    INDEX
    Explanations

    references to political figures, specifically governors and members of Congress

    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
    0:0.06
    1:0.02
    2:0.07
    3:0.05
    4:0.06
    5:0.05
    6:0.09
    7:0.04
    8:0.38
    9:0.07
    10:0.02
    11:0.03
    Negative Logits
     Samsung
    -4.02
     Argentine
    -3.90
    Samsung
    -3.82
     Azerbai
    -3.77
     Xperia
    -3.75
     Messi
    -3.74
     salsa
    -3.73
     Astros
    -3.71
     Barcelona
    -3.65
     KGB
    -3.57
    POSITIVE LOGITS
     Maine
    8.37
     Rhode
    4.83
     Vermont
    4.75
    Portland
    4.66
    aine
    4.62
     Dartmouth
    4.59
     Portland
    4.48
     Providence
    4.47
     Augusta
    4.46
     Jeanne
    4.39
    Activations Density 0.016%

    No Known Activations