© 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. 7473
    Prev
    Next
    INDEX
    Explanations

    mentions of opinions and authorship related to discussions or articles

    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
    0:0.02
    1:0.02
    2:0.06
    3:0.05
    4:0.11
    5:0.37
    6:0.03
    7:0.04
    8:0.02
    9:0.16
    10:0.01
    11:0.05
    Negative Logits
    livious
    -3.29
    Suddenly
    -3.20
    Eventually
    -3.10
     Suddenly
    -2.85
    ?",
    -2.81
     ));
    -2.73
    Enlarge
    -2.73
    ilogy
    -2.68
    ,"
    -2.63
    redibly
    -2.59
    POSITIVE LOGITS
     may
    4.28
     MAY
    4.01
     please
    3.94
     unless
    3.87
     shall
    3.85
    may
    3.71
     cannot
    3.64
     MUST
    3.54
    unless
    3.42
     PLEASE
    3.33
    Activations Density 0.623%

    No Known Activations