© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6588
    Prev
    Next
    INDEX
    Explanations

    details about sports events involving the Colorado Rapids and their opponents

    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
    0:0.07
    1:0.05
    2:0.06
    3:0.07
    4:0.03
    5:0.06
    6:0.05
    7:0.06
    8:0.36
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
     Hok
    -5.32
     Cheong
    -4.13
     Okinawa
    -4.10
     Okin
    -3.88
     Ryu
    -3.80
     Fiji
    -3.79
     Ichigo
    -3.66
     UNC
    -3.46
    Ky
    -3.39
    angan
    -3.37
    POSITIVE LOGITS
     Rapids
    6.67
    Colorado
    4.10
     Dynamo
    4.08
     Colorado
    3.98
     Lansing
    3.64
     Braz
    3.54
     Timbers
    3.40
     Avalanche
    3.25
     MLS
    3.25
     Edmonton
    3.20
    Activations Density 0.003%

    No Known Activations