© 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. 12890
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "L"

    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
    0:0.08
    1:0.03
    2:0.03
    3:0.05
    4:0.05
    5:0.19
    6:0.04
    7:0.03
    8:0.02
    9:0.33
    10:0.02
    11:0.08
    Negative Logits
    udeb
    -2.23
    anced
    -2.20
     externalToEVAOnly
    -2.20
     ejected
    -2.19
    gered
    -2.19
    etheless
    -2.17
    foreseen
    -2.14
    ustomed
    -2.14
    Said
    -2.10
    ixon
    -2.08
    POSITIVE LOGITS
     is
    3.06
     are
    2.82
     comes
    2.64
     arrives
    2.62
     proves
    2.57
    ibaba
    2.56
     we
    2.55
     begins
    2.49
     shines
    2.49
     ›
    2.49
    Activations Density 0.017%

    No Known Activations