© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 17120
    Prev
    Next
    INDEX
    Explanations

    attributes and abilities of game elements, particularly focusing on damage mechanics and player enhancements

    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
    0:0.08
    1:0.08
    2:0.10
    3:0.08
    4:0.14
    5:0.06
    6:0.08
    7:0.06
    8:0.05
    9:0.05
    10:0.06
    11:0.10
    Negative Logits
    soDeliveryDate
    -2.58
    Topics
    -2.46
    ocene
    -2.35
     Turing
    -2.33
    enegger
    -2.26
    uart
    -2.25
    USS
    -2.25
     todd
    -2.23
    acebook
    -2.19
    DonaldTrump
    -2.19
    POSITIVE LOGITS
     Cooldown
    4.57
     AoE
    4.18
     Damage
    4.07
    Cooldown
    4.05
     cooldown
    3.90
     ATK
    3.84
     Increases
    3.70
     damage
    3.60
     Enhance
    3.58
     Enemies
    3.56
    Activations Density 0.111%

    No Known Activations