© 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. 9055
    Prev
    Next
    INDEX
    Explanations

    mentions of statistical reports related to crime rates or definitions of offenses

    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
    0:0.16
    1:0.06
    2:0.05
    3:0.05
    4:0.13
    5:0.02
    6:0.21
    7:0.09
    8:0.02
    9:0.04
    10:0.05
    11:0.07
    Negative Logits
    tz
    -3.07
     Farn
    -2.90
    artney
    -2.81
    psey
    -2.77
     Pupp
    -2.73
     Asus
    -2.72
    龍喚士
    -2.70
    DK
    -2.63
    wang
    -2.61
    Engineers
    -2.61
    POSITIVE LOGITS
     crime
    7.54
    crime
    7.19
     Crime
    7.05
     crimes
    6.91
     criminals
    6.72
    Crime
    6.71
     criminal
    6.59
     criminality
    6.43
     Crim
    6.31
    criminal
    6.17
    Activations Density 0.324%

    No Known Activations