© 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. 10-ATT-KK
    11. 15533
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and events in sports history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.15
    1:0.12
    2:0.07
    3:0.06
    4:0.05
    5:0.04
    6:0.10
    7:0.08
    8:0.04
    9:0.06
    10:0.13
    11:0.05
    Negative Logits
     [|
    -3.00
    ima
    -2.98
     Hut
    -2.97
    qqa
    -2.95
    Guard
    -2.94
     Haf
    -2.92
    aeda
    -2.92
     Afgh
    -2.82
    hedon
    -2.76
     Rw
    -2.73
    POSITIVE LOGITS
     Chester
    7.17
     Canter
    4.14
     Chev
    3.82
     Butter
    3.61
    Che
    3.55
     Cheese
    3.10
    Penn
    3.09
     Borough
    3.03
     che
    3.02
    Tes
    2.98
    Activations Density 0.001%

    No Known Activations