© 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. 17367
    Prev
    Next
    INDEX
    Explanations

    mentions of key individuals and their roles in a formal context

    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
    0:0.17
    1:0.03
    2:0.06
    3:0.09
    4:0.07
    5:0.01
    6:0.16
    7:0.14
    8:0.01
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
    paio
    -3.60
    Denver
    -3.22
     Arpaio
    -2.92
     Broncos
    -2.90
     Denver
    -2.90
     Colo
    -2.88
     Nuggets
    -2.88
    Colorado
    -2.80
    veland
    -2.78
     Serial
    -2.77
    POSITIVE LOGITS
     IMF
    7.85
     Monetary
    4.77
     Krugman
    3.77
     OECD
    3.64
     concess
    3.53
     loans
    3.50
     Ripple
    3.49
    Economic
    3.46
     lending
    3.40
     Hait
    3.38
    Activations Density 0.013%

    No Known Activations