© 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. 10-ATT-KK
    11. 10866
    Prev
    Next
    INDEX
    Explanations

    system-related commands or keywords pertaining to file uploads

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.21
    1:0.05
    2:0.08
    3:0.06
    4:0.06
    5:0.03
    6:0.13
    7:0.16
    8:0.03
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
     Bowen
    -2.83
     Cantor
    -2.81
     Belichick
    -2.79
     Dai
    -2.62
    ichick
    -2.60
     Lilly
    -2.55
     Pence
    -2.55
     Watson
    -2.52
     Cot
    -2.50
     Fernandez
    -2.47
    POSITIVE LOGITS
     upload
    6.26
     Upload
    5.75
    Upload
    5.59
     uploading
    5.54
    upload
    5.26
     uploaded
    4.94
    uploads
    4.77
    pload
    3.61
     torrent
    3.50
     download
    3.38
    Activations Density 0.011%

    No Known Activations