© 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. 21768
    Prev
    Next
    INDEX
    Explanations

    references to clothing items, particularly shirts and their various characteristics

    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
    0:0.05
    1:0.04
    2:0.03
    3:0.04
    4:0.12
    5:0.02
    6:0.04
    7:0.39
    8:0.03
    9:0.05
    10:0.04
    11:0.11
    Negative Logits
     shirts
    -3.01
     Tart
    -3.00
    Stock
    -2.97
     rapists
    -2.92
    "]=>
    -2.81
     Shirt
    -2.78
     Tiffany
    -2.73
    shirts
    -2.71
     shirt
    -2.67
     Metall
    -2.67
    POSITIVE LOGITS
     Fly
    2.60
    arios
    2.52
     Macro
    2.43
    coe
    2.40
    uro
    2.32
    ieu
    2.32
    mma
    2.32
     Fallon
    2.27
    iba
    2.25
     gravy
    2.22
    Activations Density 0.004%

    No Known Activations