© 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. 10882
    Prev
    Next
    INDEX
    Explanations

    references to decision-making and reporting within the White House

    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
    0:0.08
    1:0.05
    2:0.02
    3:0.08
    4:0.05
    5:0.02
    6:0.29
    7:0.17
    8:0.01
    9:0.05
    10:0.05
    11:0.08
    Negative Logits
    liga
    -2.93
     CLR
    -2.68
    EStreamFrame
    -2.54
    Ont
    -2.52
    NetMessage
    -2.51
    Runner
    -2.48
     Mechdragon
    -2.46
    MpServer
    -2.45
    ⓘ
    -2.43
     Leth
    -2.40
    POSITIVE LOGITS
    OTUS
    4.57
     White
    4.33
     Spicer
    4.24
     Ivanka
    4.08
     aides
    4.05
     administration
    3.96
     Trump
    3.77
    White
    3.72
     Office
    3.72
     Kushner
    3.67
    Activations Density 0.229%

    No Known Activations