© 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. 15712
    Prev
    Next
    INDEX
    Explanations

    mentions of injuries or accidents related to automobile racing

    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
    0:0.21
    1:0.07
    2:0.04
    3:0.08
    4:0.04
    5:0.02
    6:0.10
    7:0.15
    8:0.01
    9:0.04
    10:0.13
    11:0.04
    Negative Logits
     Cameroon
    -3.92
     Wolves
    -3.36
     Alger
    -3.29
    Egypt
    -3.23
     Moz
    -3.09
     gor
    -3.08
     Guant
    -3.06
    Blake
    -3.03
     Blazers
    -3.02
     Mali
    -2.97
    POSITIVE LOGITS
     Indy
    7.29
     Indianapolis
    6.07
     Speedway
    5.54
     NASCAR
    4.13
    Indian
    4.09
     Racing
    4.02
     Motor
    3.85
     racer
    3.80
     racing
    3.77
     padd
    3.71
    Activations Density 0.013%

    No Known Activations