© 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. 5-ATT-KK
    11. 9958
    Prev
    Next
    INDEX
    Explanations

    repeated references to "the" as well as expressions indicating a game or competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.32
    2:0.04
    3:0.03
    4:0.03
    5:0.20
    6:0.03
    7:0.03
    8:0.05
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
     Cosponsors
    -2.23
    idium
    -2.11
    wr
    -2.08
     Hels
    -2.03
    br
    -2.00
     Coul
    -1.96
     Dil
    -1.85
     Reynolds
    -1.83
    vin
    -1.80
    roy
    -1.78
    POSITIVE LOGITS
     game
    2.46
    Game
    2.13
    game
    2.12
    aminer
    1.98
     outing
    1.94
     games
    1.93
     GAME
    1.93
     crowd
    1.88
     Game
    1.87
     gameplay
    1.86
    Activations Density 0.011%

    No Known Activations