© 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. 21938
    Prev
    Next
    INDEX
    Explanations

    references to football managers and player performances

    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
    0:0.29
    1:0.05
    2:0.05
    3:0.07
    4:0.06
    5:0.02
    6:0.06
    7:0.08
    8:0.02
    9:0.06
    10:0.14
    11:0.04
    Negative Logits
     Sands
    -3.64
     Mirage
    -3.61
     Chandra
    -3.53
     Tyson
    -3.50
     KT
    -3.43
     Blackhawks
    -3.25
     Lash
    -3.13
     RF
    -3.13
     Jagu
    -3.10
     microw
    -3.08
    POSITIVE LOGITS
    Liverpool
    4.44
     Rodgers
    4.07
     Klopp
    4.01
     Liverpool
    4.00
     Anfield
    3.88
     Wine
    3.78
    lopp
    3.74
    wine
    3.69
     Gerrard
    3.64
     Fir
    3.55
    Activations Density 0.013%

    No Known Activations