© 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. 20369
    Prev
    Next
    INDEX
    Explanations

    quoted speech or statements in the text

    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
    0:0.12
    1:0.19
    2:0.09
    3:0.04
    4:0.03
    5:0.02
    6:0.13
    7:0.10
    8:0.02
    9:0.05
    10:0.13
    11:0.04
    Negative Logits
    igi
    -3.10
    iji
    -2.96
    zbollah
    -2.95
     fir
    -2.84
     Splash
    -2.81
     MM
    -2.76
    apy
    -2.71
    iy
    -2.69
    yrim
    -2.68
    seys
    -2.66
    POSITIVE LOGITS
     Conrad
    8.66
     Cornel
    3.54
     Constant
    3.36
     Constantin
    3.22
     Laurent
    3.15
     Vald
    3.09
    Con
    3.07
     Columb
    3.06
     Constantine
    3.06
     Helena
    3.05
    Activations Density 0.000%

    No Known Activations