© 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. 6571
    Prev
    Next
    INDEX
    Explanations

    references to economic ratings and assessments

    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
    0:0.13
    1:0.04
    2:0.04
    3:0.24
    4:0.02
    5:0.02
    6:0.09
    7:0.12
    8:0.02
    9:0.04
    10:0.13
    11:0.04
    Negative Logits
     Kasich
    -3.55
     Toledo
    -3.55
     Akron
    -3.48
     Buc
    -3.35
    veland
    -3.25
    Ohio
    -3.18
     Cleveland
    -3.17
    wagen
    -3.16
    chwitz
    -3.08
    andowski
    -3.02
    POSITIVE LOGITS
     Australians
    8.63
    Australian
    8.28
     Australian
    8.20
    Australia
    8.19
     Australia
    8.11
    Austral
    8.06
     Canberra
    7.30
     Tasmania
    6.41
     Queensland
    6.39
     Sydney
    6.24
    Activations Density 0.238%

    No Known Activations