© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 1361
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to tabletop role-playing games, specifically references to Dungeons & Dragons

    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
    0:0.21
    1:0.02
    2:0.11
    3:0.10
    4:0.03
    5:0.08
    6:0.06
    7:0.05
    8:0.19
    9:0.04
    10:0.03
    11:0.04
    Negative Logits
     Eminem
    -3.04
    inventoryQuantity
    -3.02
     selfie
    -2.98
     Kendrick
    -2.90
     Kanye
    -2.89
    uv
    -2.88
     Gutierrez
    -2.88
    Houston
    -2.85
     Bieber
    -2.78
     Malone
    -2.76
    POSITIVE LOGITS
     Dungeons
    5.58
     Pathfinder
    5.00
     tabletop
    4.77
     Dungeon
    4.64
     RPGs
    4.63
     Cthulhu
    4.54
     Sorce
    4.53
     Wizards
    4.38
     RPG
    4.31
     Dice
    4.16
    Activations Density 0.077%

    No Known Activations