© 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. 5518
    Prev
    Next
    INDEX
    Explanations

    significant events involving large gatherings and celebrations

    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
    0:0.21
    1:0.02
    2:0.16
    3:0.07
    4:0.04
    5:0.08
    6:0.10
    7:0.04
    8:0.08
    9:0.08
    10:0.03
    11:0.04
    Negative Logits
    doc
    -2.99
     Locked
    -2.88
     Kindle
    -2.76
     Codec
    -2.75
     editing
    -2.69
     neurot
    -2.69
     IPM
    -2.66
     genome
    -2.65
    krit
    -2.61
     BIOS
    -2.60
    POSITIVE LOGITS
     Parade
    7.14
     parade
    6.95
     procession
    5.13
     floats
    4.46
     marching
    4.20
     marches
    4.18
     Carnival
    3.86
     march
    3.74
     festivities
    3.72
     streetcar
    3.65
    Activations Density 0.012%

    No Known Activations