© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 17102
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their related contextual phrases

    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
    0:0.07
    1:0.07
    2:0.06
    3:0.05
    4:0.20
    5:0.09
    6:0.07
    7:0.07
    8:0.05
    9:0.09
    10:0.06
    11:0.06
    Negative Logits
    "],
    -3.27
    '';
    -3.24
    !",
    -3.22
    ``
    -3.16
    ?",
    -3.14
    "},
    -3.13
    "}
    -3.04
    )",
    -3.02
    natureconservancy
    -2.97
    "]
    -2.91
    POSITIVE LOGITS
     Sporting
    2.68
     midfielder
    2.56
     goalkeeper
    2.56
     Athletic
    2.48
     striker
    2.48
     UEFA
    2.47
     Champions
    2.46
     Ahead
    2.41
     himself
    2.39
    pring
    2.30
    Activations Density 0.012%

    No Known Activations