© 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. 10-ATT-KK
    11. 17295
    Prev
    Next
    INDEX
    Explanations

    specific references to news articles or columns and their publication details

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.23
    1:0.07
    2:0.04
    3:0.09
    4:0.04
    5:0.01
    6:0.07
    7:0.13
    8:0.02
    9:0.02
    10:0.18
    11:0.03
    Negative Logits
    uador
    -4.21
     Nicaragua
    -3.70
     Voy
    -3.65
     Filip
    -3.48
     Ecuador
    -3.27
     Pai
    -3.25
     HTC
    -3.17
     GoPro
    -3.12
     dolphin
    -3.08
     Philippine
    -3.04
    POSITIVE LOGITS
     Birmingham
    8.12
    Bir
    7.32
    mingham
    5.23
     Midlands
    4.37
     Hunts
    4.27
     Shelby
    3.87
     Alabama
    3.86
     Hoover
    3.83
     Wolver
    3.70
     Hubbard
    3.69
    Activations Density 0.002%

    No Known Activations