© 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. 9-ATT-KK
    11. 6800
    Prev
    Next
    INDEX
    Explanations

    instances of teamwork and joint actions in sports events

    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
    0:0.09
    1:0.02
    2:0.07
    3:0.03
    4:0.04
    5:0.04
    6:0.20
    7:0.04
    8:0.10
    9:0.25
    10:0.03
    11:0.04
    Negative Logits
     Beth
    -3.66
     Americ
    -3.63
    olith
    -3.34
     Strongh
    -3.33
    astern
    -3.26
     cycl
    -3.25
    igham
    -3.22
    Mill
    -3.22
    Rail
    -3.22
     gymn
    -3.20
    POSITIVE LOGITS
     Suarez
    10.26
     Urug
    7.75
     Uruguay
    7.20
     Luis
    5.63
    Su
    5.04
     Edgar
    5.03
     Torres
    4.58
     Gomez
    4.40
     Su
    4.33
     Nou
    4.32
    Activations Density 0.003%

    No Known Activations