© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14998
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to human trafficking and its implications

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.02
    2:0.34
    3:0.07
    4:0.04
    5:0.09
    6:0.06
    7:0.06
    8:0.09
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
     physicists
    -3.48
     Hawking
    -2.95
     サーティワン
    -2.81
     fract
    -2.80
     annotations
    -2.74
    odox
    -2.73
     Physics
    -2.71
    oust
    -2.70
     physicist
    -2.66
     reper
    -2.60
    POSITIVE LOGITS
     Traff
    6.30
     trafficking
    6.11
     traffickers
    5.83
     traff
    5.72
     prostitution
    5.02
     pedoph
    4.42
     kidnapping
    4.20
     prostitute
    3.98
     exploitation
    3.97
     underage
    3.91
    Activations Density 0.038%

    No Known Activations