© 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. 15627
    Prev
    Next
    INDEX
    Explanations

    descriptors related to unique gaming experiences, particularly those involving groundbreaking elements in a game

    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
    0:0.07
    1:0.01
    2:0.07
    3:0.05
    4:0.04
    5:0.04
    6:0.29
    7:0.04
    8:0.09
    9:0.18
    10:0.03
    11:0.04
    Negative Logits
     sett
    -4.05
     Notting
    -3.98
     Palestine
    -3.88
     Bund
    -3.85
     Buchanan
    -3.79
     Colonial
    -3.77
     Kessler
    -3.71
     Foley
    -3.70
     Sett
    -3.67
     Lambert
    -3.60
    POSITIVE LOGITS
     Dragon
    10.33
    Dragon
    10.04
     dragon
    9.82
     dragons
    9.21
    dragon
    8.72
     DRAGON
    8.62
     Dragons
    8.35
     dracon
    6.60
     Archdemon
    5.72
     Fenrir
    5.58
    Activations Density 0.009%

    No Known Activations