© 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. 5-ATT-KK
    11. 214
    Prev
    Next
    INDEX
    Explanations

    words indicating potential, possibility, and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.38
    2:0.02
    3:0.03
    4:0.02
    5:0.14
    6:0.04
    7:0.02
    8:0.06
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
    Americ
    -2.26
    %:
    -1.97
    brance
    -1.95
    cius
    -1.83
    onym
    -1.83
    ----------
    -1.81
    女
    -1.80
    %%
    -1.78
    Mob
    -1.74
    yright
    -1.74
    POSITIVE LOGITS
    ocl
    1.85
     drag
    1.79
     Rin
    1.77
     tou
    1.71
     decon
    1.68
     disc
    1.68
     retri
    1.65
     takes
    1.64
     Equip
    1.64
     undert
    1.63
    Activations Density 0.013%

    No Known Activations