© 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. 13126
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic style and expression

    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
    1:0.05
    2:0.25
    3:0.07
    4:0.15
    5:0.07
    6:0.03
    7:0.05
    8:0.06
    9:0.05
    10:0.08
    11:0.04
    Negative Logits
     Lans
    -2.78
    anamo
    -2.72
     Hung
    -2.70
     Neville
    -2.67
    95
    -2.55
     Medina
    -2.54
     Leeds
    -2.53
     incorpor
    -2.50
     Patton
    -2.50
     administ
    -2.46
    POSITIVE LOGITS
     {
    7.23
    {
    6.51
     {}
    5.50
     {\
    5.43
    .}
    5.25
     }
    5.08
    }
    5.03
     {*
    4.83
    :{
    4.83
    ={
    4.61
    Activations Density 0.013%

    No Known Activations