© 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. 9-ATT-KK
    11. 5792
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or cities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.04
    3:0.47
    4:0.04
    5:0.07
    6:0.02
    7:0.04
    8:0.08
    9:0.02
    10:0.06
    11:0.02
    Negative Logits
     delinqu
    -2.36
    omorph
    -2.15
    acters
    -2.09
    Factor
    -2.01
    Statistics
    -2.00
    xual
    -1.99
    atech
    -1.99
     [+
    -1.95
     Individual
    -1.91
    untled
    -1.86
    POSITIVE LOGITS
     headquarters
    3.19
     Emirates
    2.97
     airports
    2.95
     Bahamas
    2.93
     hometown
    2.85
     shores
    2.75
     capitals
    2.71
     airport
    2.71
     Vatican
    2.69
     Wembley
    2.64
    Activations Density 0.929%

    No Known Activations