© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 21859
    Prev
    Next
    INDEX
    Explanations

    elements related to visual components and structures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.14
    1:0.27
    2:0.03
    3:0.05
    4:0.05
    5:0.15
    6:0.03
    7:0.03
    8:0.08
    9:0.05
    10:0.03
    11:0.03
    Negative Logits
    otrop
    -1.69
     Moss
    -1.65
    inous
    -1.64
    otropic
    -1.64
    ivas
    -1.54
    lling
    -1.53
    otine
    -1.51
    nings
    -1.50
    ipl
    -1.50
     Canaveral
    -1.47
    POSITIVE LOGITS
     |
    2.77
    |
    2.34
     ±
    2.32
     [|
    2.29
     ->
    2.16
     >>
    2.08
    _>
    2.06
     ¯
    2.04
    ->
    2.03
     ↑
    1.97
    Activations Density 0.005%

    No Known Activations