© 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. 9020
    Prev
    Next
    INDEX
    Explanations

    references to police and law enforcement organizations

    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
    0:0.06
    1:0.06
    2:0.02
    3:0.12
    4:0.06
    5:0.12
    6:0.07
    7:0.07
    8:0.03
    9:0.15
    10:0.06
    11:0.13
    Negative Logits
    ".[
    -2.56
    ."[
    -2.39
    .�
    -2.36
     theorist
    -2.33
     Luthor
    -2.32
     Lois
    -2.31
    .''
    -2.30
    ''.
    -2.28
     Montana
    -2.26
     Whitney
    -2.25
    POSITIVE LOGITS
    ews
    3.22
    …)
    2.75
    ffic
    2.65
    events
    2.60
    tyard
    2.53
    gency
    2.45
    union
    2.44
    ️
    2.39
    oyal
    2.38
    english
    2.37
    Activations Density 0.006%

    No Known Activations