© 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. 2204
    Prev
    Next
    INDEX
    Explanations

    questions regarding performance and rankings in sports contexts

    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
    0:0.09
    1:0.02
    2:0.23
    3:0.16
    4:0.06
    5:0.11
    6:0.03
    7:0.07
    8:0.07
    9:0.02
    10:0.06
    11:0.02
    Negative Logits
     externalToEVAOnly
    -2.87
     interf
    -2.79
     cafe
    -2.67
    unction
    -2.62
    peace
    -2.54
    bara
    -2.39
    aura
    -2.37
    kun
    -2.32
     synagogue
    -2.27
    atom
    -2.26
    POSITIVE LOGITS
     rankings
    5.04
     Rankings
    4.89
     rosters
    4.73
     preseason
    4.51
     Ranking
    4.25
    Players
    4.24
    Football
    4.15
     quarterbacks
    4.14
     ranking
    4.09
     ranked
    4.07
    Activations Density 0.458%

    No Known Activations