© 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. 14807
    Prev
    Next
    INDEX
    Explanations

    references to specific competitive events or cups

    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
    0:0.10
    1:0.04
    2:0.06
    3:0.06
    4:0.04
    5:0.04
    6:0.23
    7:0.03
    8:0.09
    9:0.20
    10:0.02
    11:0.04
    Negative Logits
     ROCK
    -4.51
    Hunter
    -4.35
     Reyes
    -4.26
     Hunter
    -4.17
    Rock
    -4.15
     Jindal
    -3.99
     lizard
    -3.97
     Hyder
    -3.79
     JS
    -3.78
     Osiris
    -3.73
    POSITIVE LOGITS
     cup
    9.37
     cups
    9.10
     Cup
    8.91
     Cups
    8.56
    cup
    8.27
     Bowl
    4.58
     coffee
    4.39
    bowl
    4.36
     Mug
    4.25
     Starbucks
    4.22
    Activations Density 0.005%

    No Known Activations