© 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. 21831
    Prev
    Next
    INDEX
    Explanations

    phrases related to percentages or integers representing quantities

    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
    1:0.03
    2:0.03
    3:0.06
    4:0.50
    5:0.03
    6:0.05
    7:0.04
    8:0.06
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
    [/
    -5.91
    ".[
    -5.66
    "],
    -5.51
    '';
    -5.29
    ',"
    -4.99
    "]
    -4.89
    ''.
    -4.78
    "},
    -4.62
    "}
    -4.38
     [/
    -4.34
    POSITIVE LOGITS
     dreaded
    2.54
    irst
    2.35
    —-
    2.24
     disgusted
    2.17
     horrifying
    2.13
     hated
    2.09
     disgusting
    2.01
     nause
    1.97
     frown
    1.96
     ****
    1.94
    Activations Density 0.003%

    No Known Activations