© 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. 6345
    Prev
    Next
    INDEX
    Explanations

    references to quantity and variety of items or concepts

    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
    0:0.04
    1:0.04
    2:0.06
    3:0.14
    4:0.03
    5:0.05
    6:0.03
    7:0.08
    8:0.03
    9:0.02
    10:0.37
    11:0.04
    Negative Logits
     disadvantage
    -2.09
    uces
    -1.95
    felt
    -1.95
    prev
    -1.83
    benef
    -1.77
     advantageous
    -1.76
    idity
    -1.71
    oston
    -1.67
    iquette
    -1.67
    ober
    -1.65
    POSITIVE LOGITS
     innumerable
    2.71
     Numerous
    2.54
    cellaneous
    2.41
     Dozens
    2.34
     assortment
    2.31
     assorted
    2.29
     plethora
    2.27
     countless
    2.27
    Various
    2.23
     myriad
    2.20
    Activations Density 0.444%

    No Known Activations