© 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. 15916
    Prev
    Next
    INDEX
    Explanations

    historical references related to military enlistment and recruitment events

    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
    0:0.30
    1:0.03
    2:0.07
    3:0.09
    4:0.06
    5:0.02
    6:0.06
    7:0.16
    8:0.02
    9:0.04
    10:0.05
    11:0.03
    Negative Logits
     NV
    -3.62
     Scientology
    -3.31
     KT
    -2.99
     Elon
    -2.96
    NV
    -2.93
     Oracle
    -2.92
    Oracle
    -2.85
     Nex
    -2.80
    Scient
    -2.79
     Misc
    -2.78
    POSITIVE LOGITS
     1916
    5.65
     1915
    5.38
     1917
    5.28
     1918
    5.12
     1914
    5.10
     1919
    4.72
     1912
    4.56
     1913
    4.47
     Bolshe
    4.42
     1911
    4.25
    Activations Density 0.044%

    No Known Activations