© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 17354
    Prev
    Next
    INDEX
    Explanations

    questions and expressions related to uncertainty or inquiry

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.16
    1:0.11
    2:0.05
    3:0.04
    4:0.02
    5:0.02
    6:0.16
    7:0.13
    8:0.02
    9:0.03
    10:0.17
    11:0.04
    Negative Logits
    Pand
    -3.14
     Lone
    -2.58
    Oak
    -2.56
     Xuan
    -2.47
    flower
    -2.45
    isons
    -2.43
     feral
    -2.41
     McAuliffe
    -2.41
     Xi
    -2.36
    inance
    -2.36
    POSITIVE LOGITS
     Ser
    8.63
    Ser
    7.29
     ser
    5.86
    ser
    5.39
     Serbian
    4.72
     Serbia
    4.52
     SER
    4.09
    SER
    3.63
     serum
    3.41
     Kosovo
    3.34
    Activations Density 0.013%

    No Known Activations