© 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. 6480
    Prev
    Next
    INDEX
    Explanations

    elements related to notoriety and moral judgments

    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
    0:0.08
    1:0.02
    2:0.08
    3:0.04
    4:0.05
    5:0.04
    6:0.24
    7:0.04
    8:0.05
    9:0.26
    10:0.02
    11:0.03
    Negative Logits
     dot
    -3.59
     berries
    -3.58
     Kramer
    -3.58
    wig
    -3.57
     Doodle
    -3.56
     Ukrain
    -3.38
     Lyme
    -3.37
     Patriot
    -3.37
     Celtic
    -3.33
     Lithuan
    -3.31
    POSITIVE LOGITS
     Esc
    9.72
    Esc
    9.50
     esc
    7.04
    esc
    6.81
     ESC
    5.77
     Escape
    5.15
    escape
    4.87
     escort
    4.54
     Carr
    4.05
     Fal
    3.93
    Activations Density 0.002%

    No Known Activations