© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 1473
    Prev
    Next
    INDEX
    Explanations

    statistical data related to player performance in sports

    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
    0:0.05
    1:0.02
    2:0.05
    3:0.16
    4:0.03
    5:0.29
    6:0.03
    7:0.10
    8:0.11
    9:0.02
    10:0.05
    11:0.03
    Negative Logits
     96
    -3.55
     350
    -3.51
     160
    -3.43
     400
    -3.40
     850
    -3.38
     10000
    -3.38
     408
    -3.38
     336
    -3.37
     280
    -3.37
     256
    -3.33
    POSITIVE LOGITS
     satire
    2.79
     remedy
    2.75
     scapego
    2.73
     hypocritical
    2.71
     sham
    2.69
     tacit
    2.67
     chast
    2.63
     bondage
    2.62
     shif
    2.62
     worm
    2.61
    Activations Density 0.004%

    No Known Activations