© 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. 22187
    Prev
    Next
    INDEX
    Explanations

    names of locations, particularly cities and regions

    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
    0:0.22
    1:0.21
    2:0.03
    3:0.07
    4:0.03
    5:0.02
    6:0.10
    7:0.07
    8:0.02
    9:0.02
    10:0.11
    11:0.03
    Negative Logits
     Erdogan
    -3.90
     Enlight
    -3.44
     Vaj
    -3.38
     Tibetan
    -3.33
     dh
    -3.18
     Indonesian
    -3.15
     Erd
    -3.14
     Shah
    -3.12
     yog
    -3.00
     Dh
    -2.88
    POSITIVE LOGITS
    ville
    5.51
    VILLE
    4.46
     Spur
    3.58
     Charleston
    3.54
     Corvette
    3.52
     Chev
    3.47
    rolet
    3.38
     Carolina
    3.33
    Marie
    3.29
    Charl
    3.25
    Activations Density 0.001%

    No Known Activations