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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10736
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and sickness

    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
    0:0.06
    1:0.04
    2:0.13
    3:0.04
    4:0.04
    5:0.05
    6:0.23
    7:0.04
    8:0.03
    9:0.24
    10:0.02
    11:0.02
    Negative Logits
     Zhou
    -3.61
    ulia
    -3.57
    imble
    -3.52
    ragon
    -3.36
    arov
    -3.32
    ixel
    -3.32
    VB
    -3.30
     Decoder
    -3.27
    iframe
    -3.26
     Zimmerman
    -3.23
    POSITIVE LOGITS
     sick
    7.88
     Sick
    7.82
     sickness
    7.67
     illness
    5.92
     illnesses
    5.66
    health
    4.22
    Health
    4.13
     coughing
    4.11
     cured
    4.06
     health
    4.02
    Activations Density 0.003%

    No Known Activations