© 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. 1167
    Prev
    Next
    INDEX
    Explanations

    terms related to video game mechanics and related titles

    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
    0:0.11
    1:0.04
    2:0.07
    3:0.06
    4:0.04
    5:0.06
    6:0.09
    7:0.04
    8:0.28
    9:0.07
    10:0.04
    11:0.03
    Negative Logits
     Boone
    -3.48
    inois
    -3.48
    Je
    -3.29
     wildfire
    -3.27
     charism
    -3.24
     Bears
    -3.09
    Bear
    -3.03
    Chicago
    -3.02
    >[
    -3.02
     choir
    -3.01
    POSITIVE LOGITS
     Metroid
    8.18
     Ridley
    4.73
    roid
    4.11
     Nintendo
    3.99
     Federation
    3.97
    Nintendo
    3.96
     Frieza
    3.92
     PAL
    3.90
     NES
    3.88
     Atl
    3.74
    Activations Density 0.001%

    No Known Activations