© 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. 9-ATT-KK
    11. 6332
    Prev
    Next
    INDEX
    Explanations

    references to specific comic book characters and elements, particularly related to "Green Lantern."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.07
    1:0.02
    2:0.06
    3:0.11
    4:0.03
    5:0.06
    6:0.04
    7:0.07
    8:0.37
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
     Naples
    -3.13
     Vanderbilt
    -3.11
    ovic
    -3.03
    inen
    -2.96
    enza
    -2.94
     stroke
    -2.85
    Japan
    -2.75
    omez
    -2.71
    fecture
    -2.69
     rebound
    -2.67
    POSITIVE LOGITS
     Lantern
    4.15
     Jinn
    3.66
     Krypt
    3.62
     Venom
    3.22
     Doomsday
    3.11
     Saur
    3.06
     Rath
    3.03
     Tel
    2.94
     Packers
    2.93
     Guru
    2.91
    Activations Density 0.003%

    No Known Activations