© 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. 17184
    Prev
    Next
    INDEX
    Explanations

    references to locations, specifically cities or towns

    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
    0:0.37
    1:0.05
    2:0.06
    3:0.06
    4:0.05
    5:0.04
    6:0.06
    7:0.07
    8:0.04
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
     tar
    -4.19
     Blizz
    -3.79
     Salt
    -3.50
     Tos
    -3.50
     bow
    -3.50
     Messi
    -3.50
     Centauri
    -3.46
     Baylor
    -3.45
     Seoul
    -3.40
     Buenos
    -3.40
    POSITIVE LOGITS
     Saunders
    5.30
     Rochester
    4.76
     Cycl
    4.01
    hester
    3.74
     Monroe
    3.57
     Pry
    3.56
     Synd
    3.51
     Clone
    3.47
    onic
    3.35
     Egg
    3.32
    Activations Density 0.000%

    No Known Activations