© 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. 24314
    Prev
    Next
    INDEX
    Explanations

    references to sports, leagues, and competitive 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
    0:0.03
    1:0.01
    2:0.04
    3:0.19
    4:0.02
    5:0.08
    6:0.01
    7:0.06
    8:0.04
    9:0.01
    10:0.44
    11:0.02
    Negative Logits
    nesday
    -3.55
    uesday
    -2.69
     tomorrow
    -2.55
     timely
    -2.51
     Mondays
    -2.40
     midnight
    -2.40
    ursday
    -2.34
     Fridays
    -2.22
     Thurs
    -2.20
    today
    -2.17
    POSITIVE LOGITS
    Joined
    1.93
    advertising
    1.80
     Stud
    1.78
     owning
    1.78
    SEE
    1.76
     Mechdragon
    1.75
     studied
    1.69
     veget
    1.67
    olars
    1.65
     captivity
    1.64
    Activations Density 0.143%

    No Known Activations