© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10972
    Prev
    Next
    INDEX
    Explanations

    elements related to dungeon mechanics and progression in gaming contexts

    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
    0:0.16
    1:0.02
    2:0.17
    3:0.09
    4:0.03
    5:0.07
    6:0.08
    7:0.06
    8:0.12
    9:0.07
    10:0.04
    11:0.03
    Negative Logits
     Canad
    -2.95
     NAACP
    -2.88
    colm
    -2.88
     reciproc
    -2.81
     bourbon
    -2.77
    amsung
    -2.76
     McInt
    -2.67
     adoption
    -2.64
     patriotism
    -2.55
     Viet
    -2.53
    POSITIVE LOGITS
     dungeon
    6.77
     dungeons
    6.07
     Dungeon
    5.58
    boss
    5.44
    Boss
    5.23
     bosses
    4.96
     boss
    4.90
     Hades
    4.50
     Dungeons
    4.47
     monsters
    4.46
    Activations Density 0.019%

    No Known Activations