© 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. 10741
    Prev
    Next
    INDEX
    Explanations

    references to judicial processes and opinions

    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
    0:0.08
    1:0.02
    2:0.08
    3:0.03
    4:0.05
    5:0.04
    6:0.23
    7:0.04
    8:0.09
    9:0.23
    10:0.03
    11:0.03
    Negative Logits
     Elliott
    -4.04
     Tokens
    -3.73
     Elliot
    -3.65
     Everton
    -3.62
     GEAR
    -3.61
     Forsaken
    -3.52
     Shiny
    -3.39
     Doug
    -3.37
    DK
    -3.37
     Bahá
    -3.30
    POSITIVE LOGITS
    Nap
    11.09
     Nap
    10.83
     nap
    5.87
    apo
    5.69
     Naples
    5.57
     Napoleon
    4.79
     Rap
    4.45
     pies
    4.31
     Moz
    4.18
    Rap
    4.11
    Activations Density 0.003%

    No Known Activations