© 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. 9-ATT-KK
    11. 6435
    Prev
    Next
    INDEX
    Explanations

    terms related to crime and criminality

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.06
    1:0.01
    2:0.07
    3:0.07
    4:0.03
    5:0.06
    6:0.04
    7:0.07
    8:0.46
    9:0.03
    10:0.02
    11:0.02
    Negative Logits
    ø
    -4.51
     Copenhagen
    -4.37
     Glou
    -4.20
     Danish
    -4.16
     Celtics
    -4.08
     Norfolk
    -3.98
     Cambridge
    -3.92
     Denmark
    -3.91
     Dunk
    -3.79
     Worcester
    -3.69
    POSITIVE LOGITS
     Mexican
    7.91
    Mexico
    7.80
     Mexicans
    7.76
    Mex
    7.62
     Mexico
    6.99
     Mex
    6.55
     pes
    6.04
     Guerrero
    5.99
     cartel
    5.76
     corrid
    5.69
    Activations Density 0.142%

    No Known Activations