© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20345
    Prev
    Next
    INDEX
    Explanations

    numeric data related to statistics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.07
    3:0.10
    4:0.04
    5:0.06
    6:0.03
    7:0.08
    8:0.06
    9:0.04
    10:0.33
    11:0.04
    Negative Logits
     freely
    -2.58
     readily
    -2.48
     easily
    -2.43
     inexpensive
    -2.34
     someday
    -2.31
     privately
    -2.30
     cheaply
    -2.29
     onward
    -2.21
    iphany
    -2.17
     "\
    -2.13
    POSITIVE LOGITS
    andals
    2.18
    monton
    2.14
     intervening
    2.03
    chwitz
    1.93
    selection
    1.92
    emale
    1.90
    uty
    1.90
    GP
    1.88
     appell
    1.84
     logos
    1.81
    Activations Density 0.004%

    No Known Activations