© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 2685
    Prev
    Next
    INDEX
    Explanations

    references to the Montreal Canadiens hockey team and related discussions

    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
    0:0.08
    1:0.03
    2:0.04
    3:0.06
    4:0.04
    5:0.05
    6:0.08
    7:0.03
    8:0.37
    9:0.09
    10:0.03
    11:0.03
    Negative Logits
    Alabama
    -4.53
     Alabama
    -4.14
    Kansas
    -4.03
    Virginia
    -3.97
     Cherokee
    -3.96
     Appalachian
    -3.91
     Myanmar
    -3.73
     Hyundai
    -3.69
     Appalach
    -3.69
     Jacksonville
    -3.66
    POSITIVE LOGITS
     Montreal
    9.22
     Canadiens
    8.50
     Quebec
    7.61
     Qué
    7.21
     McGill
    7.09
     franc
    6.49
     É
    5.35
     Ré
    5.33
    ét
    5.27
    É
    5.18
    Activations Density 0.020%

    No Known Activations