© 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. 23298
    Prev
    Next
    INDEX
    Explanations

    instances of significant events or actions involving law enforcement

    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
    0:0.11
    1:0.15
    2:0.10
    3:0.05
    4:0.05
    5:0.03
    6:0.09
    7:0.08
    8:0.04
    9:0.06
    10:0.15
    11:0.05
    Negative Logits
    MAC
    -3.09
     Astro
    -3.02
     Aph
    -3.02
    oming
    -2.97
     Ast
    -2.97
     Mich
    -2.90
     Mech
    -2.89
     Merc
    -2.88
    ы
    -2.82
     vulner
    -2.79
    POSITIVE LOGITS
     Dunn
    7.44
     Croat
    3.82
     Croatian
    3.77
     UD
    3.64
     Redd
    3.44
     Rwanda
    3.35
     Trayvon
    3.26
     Cunningham
    3.25
     Riley
    3.21
     Semin
    3.19
    Activations Density 0.000%

    No Known Activations