© 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. 12338
    Prev
    Next
    INDEX
    Explanations

    mentions of notable athletes and their performance attributes

    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
    1:0.03
    2:0.03
    3:0.04
    4:0.28
    5:0.06
    6:0.05
    7:0.11
    8:0.03
    9:0.12
    10:0.02
    11:0.10
    Negative Logits
     Discussion
    -2.68
     weeping
    -2.63
    Dear
    -2.55
    DragonMagazine
    -2.54
    ��
    -2.50
     discontinued
    -2.48
    essage
    -2.48
     crem
    -2.43
    yna
    -2.40
     depicting
    -2.37
    POSITIVE LOGITS
     agility
    4.16
     athleticism
    3.63
     versatility
    3.56
     explos
    3.21
     toughness
    3.12
     defensively
    3.07
     versatile
    3.05
     deft
    3.04
     agile
    3.04
     instincts
    3.03
    Activations Density 0.361%

    No Known Activations