© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 13473
    Prev
    Next
    INDEX
    Explanations

    references to criminal activities and law enforcement actions

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

    No Comments

    Head Attr Weights
    0:0.25
    1:0.08
    2:0.09
    3:0.05
    4:0.03
    5:0.02
    6:0.09
    7:0.12
    8:0.02
    9:0.04
    10:0.12
    11:0.03
    Negative Logits
     dinosaurs
    -3.67
     dinosaur
    -3.43
     gobl
    -3.42
     ponies
    -3.41
     Dum
    -3.36
     ivory
    -3.24
     Pony
    -3.12
     coal
    -3.05
     elephants
    -3.03
     repro
    -3.03
    POSITIVE LOGITS
     Hernandez
    10.29
    ernandez
    6.45
     Hond
    5.14
     Fernandez
    5.05
     Honduras
    5.03
     Ortiz
    4.87
     Diaz
    4.42
     Alonso
    4.38
     Gonzalez
    4.32
     Gomez
    4.08
    Activations Density 0.003%

    No Known Activations