© 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 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. 8596
    Prev
    Next
    INDEX
    Explanations

    references to recipes, cooking, and food preparation

    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
    0:0.03
    1:0.02
    2:0.04
    3:0.03
    4:0.04
    5:0.48
    6:0.02
    7:0.03
    8:0.02
    9:0.17
    10:0.03
    11:0.03
    Negative Logits
    arthed
    -3.12
    �
    -2.92
    龍
    -2.92
    etheless
    -2.87
    ーティ
    -2.77
    released
    -2.70
    oxin
    -2.62
    戦
    -2.62
     ALSO
    -2.58
    )|
    -2.54
    POSITIVE LOGITS
     click
    3.13
     we
    3.01
     you
    3.00
     simplest
    2.97
     proceed
    2.91
     please
    2.73
    click
    2.66
     oneself
    2.64
     succinct
    2.61
     simply
    2.57
    Activations Density 0.116%

    No Known Activations