© 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. 16405
    Prev
    Next
    INDEX
    Explanations

    issues related to societal problems and debates

    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
    2:0.05
    3:0.04
    4:0.05
    5:0.49
    6:0.02
    7:0.03
    8:0.02
    9:0.13
    10:0.01
    11:0.05
    Negative Logits
     Eventually
    -3.16
     Previously
    -2.97
     eventually
    -2.96
     earliest
    -2.94
     BEFORE
    -2.83
    possibly
    -2.73
     before
    -2.69
    Eventually
    -2.67
     Wouldn
    -2.61
     Originally
    -2.58
    POSITIVE LOGITS
     nor
    4.54
    .;
    4.18
     either
    4.17
     anymore
    4.15
    ;
    3.82
     or
    3.19
    nor
    3.18
     ;
    3.17
    %;
    3.00
    Or
    2.90
    Activations Density 0.454%

    No Known Activations