© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-ATT-KK
    11. 15210
    Prev
    Next
    INDEX
    Explanations

    topics related to ongoing processes or actions

    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
    0:0.01
    1:0.02
    2:0.03
    3:0.04
    4:0.04
    5:0.61
    6:0.01
    7:0.03
    8:0.01
    9:0.10
    10:0.01
    11:0.03
    Negative Logits
    yip
    -3.73
    utenant
    -3.07
    ��
    -2.76
     suddenly
    -2.74
     rupture
    -2.64
    azo
    -2.64
    ワン
    -2.61
    romancer
    -2.60
     THEN
    -2.56
     urgently
    -2.46
    POSITIVE LOGITS
     until
    5.73
     despite
    5.62
     till
    5.23
    until
    5.00
     indefinitely
    4.96
    despite
    4.86
     even
    4.39
     notwithstanding
    4.37
     throughout
    4.30
     regardless
    4.25
    Activations Density 0.767%

    No Known Activations