© 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. 11881
    Prev
    Next
    INDEX
    Explanations

    specific dates and references to elections

    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
    0:0.09
    1:0.04
    2:0.02
    3:0.04
    4:0.03
    5:0.02
    6:0.31
    7:0.20
    8:0.01
    9:0.10
    10:0.03
    11:0.07
    Negative Logits
     Jur
    -3.00
     Charter
    -2.90
     City
    -2.77
    City
    -2.71
     ordinances
    -2.69
     Class
    -2.67
    ayson
    -2.64
    uckland
    -2.64
    Council
    -2.58
     Bombay
    -2.53
    POSITIVE LOGITS
     landslide
    3.13
     brig
    2.85
     landsl
    2.67
     sweeps
    2.47
     hacks
    2.47
     guiName
    2.45
    ELF
    2.44
    STE
    2.38
     rigged
    2.35
    onne
    2.29
    Activations Density 0.004%

    No Known Activations