© 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. 23277
    Prev
    Next
    INDEX
    Explanations

    references to inappropriate comments or behavior toward women

    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
    0:0.24
    1:0.05
    2:0.04
    3:0.06
    4:0.06
    5:0.03
    6:0.12
    7:0.10
    8:0.04
    9:0.10
    10:0.04
    11:0.06
    Negative Logits
     Liu
    -3.97
     vacc
    -3.12
     Worcester
    -2.99
     Azure
    -2.82
     Blockchain
    -2.77
     Interstellar
    -2.74
     Hamas
    -2.72
     Jiang
    -2.72
     Mines
    -2.70
     Pyr
    -2.70
    POSITIVE LOGITS
     tapes
    3.59
     Hannity
    3.49
     Paula
    3.46
     tape
    3.45
    Sexual
    3.36
     sexual
    3.33
     Sexual
    3.24
     taped
    3.17
     Tape
    3.11
     condom
    3.10
    Activations Density 0.001%

    No Known Activations