© 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. 12083
    Prev
    Next
    INDEX
    Explanations

    statements or assertions about opinions or beliefs

    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
    0:0.19
    1:0.11
    2:0.08
    3:0.03
    4:0.04
    5:0.03
    6:0.07
    7:0.13
    8:0.02
    9:0.05
    10:0.16
    11:0.04
    Negative Logits
     Lumpur
    -3.10
     Philippine
    -2.92
     phosphate
    -2.91
    Pak
    -2.85
     Mang
    -2.81
    uterte
    -2.79
    Forge
    -2.77
     Kry
    -2.76
    Che
    -2.73
     module
    -2.72
    POSITIVE LOGITS
     Eli
    8.91
     Levi
    4.46
     Manning
    4.14
     Giants
    3.75
     Peyton
    3.75
     Eliot
    3.57
     Naomi
    3.56
     Ethan
    3.52
     Lilly
    3.52
     Lev
    3.47
    Activations Density 0.001%

    No Known Activations