© 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. 5-ATT-KK
    11. 47046
    Prev
    Next
    INDEX
    Explanations

    words related to sexual acts and behaviors

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.05
    3:0.05
    4:0.16
    5:0.03
    6:0.08
    7:0.22
    8:0.03
    9:0.03
    10:0.17
    11:0.09
    Negative Logits
    utenant
    -1.52
     redund
    -1.45
    rolet
    -1.43
     characterization
    -1.43
     justification
    -1.41
     struggle
    -1.41
     contested
    -1.37
     brunt
    -1.35
     marginalized
    -1.35
    zinski
    -1.35
    POSITIVE LOGITS
    uba
    1.68
     221
    1.60
    ubes
    1.52
    thumbnails
    1.48
     Poles
    1.40
    asso
    1.39
     432
    1.38
    doors
    1.37
    uously
    1.37
     1024
    1.35
    Activations Density 0.000%

    No Known Activations