© 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. 10725
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding taboo relationships and legal regulations regarding marriage

    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
    0:0.22
    1:0.07
    2:0.05
    3:0.05
    4:0.07
    5:0.01
    6:0.10
    7:0.11
    8:0.01
    9:0.04
    10:0.15
    11:0.06
    Negative Logits
    闘
    -3.69
    inelli
    -3.13
    enegger
    -3.12
    inventoryQuantity
    -3.06
    utsche
    -3.05
     dstg
    -3.05
     Toro
    -3.02
     actionGroup
    -3.00
     Torch
    -2.94
     Canaver
    -2.92
    POSITIVE LOGITS
     polygamy
    8.33
     polyg
    6.80
     monog
    5.83
    poly
    5.56
    Poly
    5.48
     Mormon
    5.36
     Mormons
    4.97
     Mormonism
    4.78
     poly
    4.72
     plural
    4.68
    Activations Density 0.003%

    No Known Activations