© 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. 19657
    Prev
    Next
    INDEX
    Explanations

    terms related to health and injury severity

    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
    0:0.04
    1:0.04
    2:0.02
    3:0.05
    4:0.07
    5:0.03
    6:0.03
    7:0.41
    8:0.03
    9:0.08
    10:0.03
    11:0.11
    Negative Logits
    crim
    -2.62
    DERR
    -2.39
     DEFENSE
    -2.35
    romy
    -2.33
     Brist
    -2.23
     Complex
    -2.23
     Cran
    -2.23
     Crim
    -2.23
     Calder
    -2.22
     scram
    -2.22
    POSITIVE LOGITS
    esta
    2.70
     Riyadh
    2.59
     Uganda
    2.58
    uko
    2.57
     plantation
    2.55
     Olsen
    2.52
     Xi
    2.48
    ela
    2.47
     Hawai
    2.47
     Ellison
    2.46
    Activations Density 0.005%

    No Known Activations