© 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. 17168
    Prev
    Next
    INDEX
    Explanations

    instances of permit-related terminology and discussions surrounding legal permissions

    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
    0:0.11
    1:0.04
    2:0.05
    3:0.06
    4:0.06
    5:0.02
    6:0.21
    7:0.16
    8:0.03
    9:0.04
    10:0.06
    11:0.10
    Negative Logits
    reet
    -2.73
    oyal
    -2.66
    Sent
    -2.61
    ileaks
    -2.57
    rug
    -2.47
     Prol
    -2.44
     Akin
    -2.42
     Petraeus
    -2.39
    aspers
    -2.31
    boxing
    -2.30
    POSITIVE LOGITS
     permits
    4.94
     permit
    4.85
     zoning
    3.48
     permitting
    3.46
     approvals
    3.35
     licences
    3.12
     licenses
    3.10
     permission
    3.07
     ordinances
    2.96
     licence
    2.88
    Activations Density 0.026%

    No Known Activations