© 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. 6504
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and statistics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.06
    2:0.05
    3:0.37
    4:0.04
    5:0.03
    6:0.08
    7:0.07
    8:0.02
    9:0.05
    10:0.05
    11:0.07
    Negative Logits
    bernatorial
    -3.37
    inventoryQuantity
    -2.97
    gomery
    -2.94
    geoning
    -2.86
    ellar
    -2.72
    actionDate
    -2.69
     サーティワン
    -2.67
    utenberg
    -2.62
    odox
    -2.62
    ertodd
    -2.60
    POSITIVE LOGITS
     Italy
    6.65
     Finland
    6.65
     Brazil
    6.57
    Italy
    6.54
     Argentina
    6.52
     Spain
    6.49
     France
    6.40
     Portugal
    6.39
     Romania
    6.38
     Peru
    6.34
    Activations Density 0.629%

    No Known Activations