© 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. 3883
    Prev
    Next
    INDEX
    Explanations

    terms related to sports statistics and performance metrics

    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
    0:0.06
    1:0.03
    2:0.11
    3:0.09
    4:0.04
    5:0.07
    6:0.06
    7:0.06
    8:0.27
    9:0.06
    10:0.06
    11:0.04
    Negative Logits
     Myanmar
    -3.61
     Burma
    -3.38
    Bang
    -3.09
    anmar
    -3.02
     Rohingya
    -2.94
     Jericho
    -2.92
    imbabwe
    -2.89
     Kimber
    -2.86
    Wan
    -2.81
     bamboo
    -2.80
    POSITIVE LOGITS
     Cors
    6.49
     Canadiens
    4.07
    orsi
    3.61
     Cout
    3.50
     linem
    3.24
     Finland
    3.12
     Helsinki
    3.09
     Catalonia
    3.06
     Avalanche
    2.94
     Alps
    2.91
    Activations Density 0.001%

    No Known Activations