© 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. 6709
    Prev
    Next
    INDEX
    Explanations

    statements about expectations and comparisons regarding a show's quality or performance

    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
    0:0.20
    1:0.07
    2:0.06
    3:0.07
    4:0.06
    5:0.03
    6:0.10
    7:0.11
    8:0.02
    9:0.05
    10:0.14
    11:0.04
    Negative Logits
    obyl
    -3.48
     CAS
    -3.36
     carcin
    -3.30
     chrom
    -3.20
     Romanian
    -3.03
     resil
    -3.02
     ozone
    -2.95
     Venus
    -2.94
     HP
    -2.91
    chrom
    -2.88
    POSITIVE LOGITS
     Fargo
    10.02
     Dakota
    4.62
    Minnesota
    4.02
     Sioux
    3.97
     Minneapolis
    3.92
     Esk
    3.86
     Dul
    3.73
     Minnesota
    3.70
     Omaha
    3.65
     MN
    3.57
    Activations Density 0.001%

    No Known Activations