© 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. 8164
    Prev
    Next
    INDEX
    Explanations

    references to external military presence and national security

    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
    0:0.26
    1:0.03
    2:0.03
    3:0.10
    4:0.04
    5:0.01
    6:0.07
    7:0.13
    8:0.03
    9:0.03
    10:0.17
    11:0.04
    Negative Logits
    Haw
    -4.36
     LSU
    -4.11
    haw
    -3.90
     Hawth
    -3.88
     Newton
    -3.72
    Houston
    -3.67
     Baton
    -3.62
     SG
    -3.49
     Alvin
    -3.48
     Haw
    -3.48
    POSITIVE LOGITS
     Polish
    8.95
     Warsaw
    8.80
     Poland
    8.55
     Poles
    8.44
    Pol
    7.47
    ł
    6.95
     Lithuan
    5.81
    Wars
    5.67
     Lithuania
    5.41
     Auschwitz
    5.29
    Activations Density 0.054%

    No Known Activations