© 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. 13049
    Prev
    Next
    INDEX
    Explanations

    references to specific game mechanics or actions related to gameplay

    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
    0:0.03
    1:0.02
    2:0.04
    3:0.11
    4:0.05
    5:0.06
    6:0.02
    7:0.05
    8:0.02
    9:0.03
    10:0.51
    11:0.01
    Negative Logits
    %);
    -2.01
     continuing
    -1.83
    RIP
    -1.77
    .),
    -1.73
     continuation
    -1.71
    .).
    -1.70
     awaiting
    -1.68
    _.
    -1.68
    rats
    -1.67
    }.
    -1.64
    POSITIVE LOGITS
     requires
    3.52
     involves
    2.93
     would
    2.83
     entails
    2.73
     constitutes
    2.73
     wouldn
    2.66
     eliminates
    2.61
     creates
    2.61
     makes
    2.58
     ensures
    2.57
    Activations Density 0.569%

    No Known Activations