© 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. 15475
    Prev
    Next
    INDEX
    Explanations

    terms related to vegan dietary substitutes and their culinary applications

    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
    0:0.24
    1:0.07
    2:0.05
    3:0.06
    4:0.05
    5:0.04
    6:0.07
    7:0.12
    8:0.02
    9:0.05
    10:0.10
    11:0.07
    Negative Logits
     Mek
    -3.07
    River
    -2.92
     downstream
    -2.78
     Budapest
    -2.77
     Akin
    -2.73
     poetry
    -2.69
    andowski
    -2.68
     XY
    -2.68
     Lamar
    -2.64
     upstream
    -2.62
    POSITIVE LOGITS
     nut
    6.07
     nuts
    6.03
     almonds
    5.67
    nuts
    5.34
     wal
    5.34
     cas
    4.91
     almond
    4.64
    Nut
    4.60
    nut
    4.55
     peanuts
    4.32
    Activations Density 0.005%

    No Known Activations