© 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. 10-ATT-KK
    11. 13880
    Prev
    Next
    INDEX
    Explanations

    references to gaming mechanics and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.05
    2:0.14
    3:0.04
    4:0.10
    5:0.04
    6:0.09
    7:0.13
    8:0.02
    9:0.05
    10:0.12
    11:0.07
    Negative Logits
     Beng
    -3.04
    ���
    -2.88
    �
    -2.63
     Stevenson
    -2.61
     Lag
    -2.47
    LO
    -2.47
    Lind
    -2.46
    Bloom
    -2.39
    �
    -2.34
    MK
    -2.32
    POSITIVE LOGITS
     dice
    6.28
     Dice
    5.80
     rolls
    3.91
     roll
    3.22
     rolled
    3.18
     rou
    3.06
     die
    3.03
     rolling
    3.02
     dots
    2.85
     tiles
    2.77
    Activations Density 0.004%

    No Known Activations