© 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. 6378
    Prev
    Next
    INDEX
    Explanations

    statements and comparisons related to relationships and their dynamics

    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
    1:0.06
    2:0.08
    3:0.06
    4:0.05
    5:0.09
    6:0.15
    7:0.08
    8:0.08
    9:0.12
    10:0.03
    11:0.08
    Negative Logits
     BG
    -3.57
     atheist
    -3.39
    izon
    -3.15
     Zionism
    -3.00
     Balloon
    -2.97
     atheists
    -2.92
     Manson
    -2.88
     Sikh
    -2.87
     balloon
    -2.86
     atheism
    -2.84
    POSITIVE LOGITS
    Jun
    5.84
     Junior
    5.59
     jun
    5.52
     Jun
    5.25
     Soph
    5.01
     freshmen
    4.15
     soph
    4.15
     junior
    4.02
    jun
    4.00
     Senior
    3.93
    Activations Density 0.002%

    No Known Activations