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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6837
    Prev
    Next
    INDEX
    Explanations

    references to numerical statistics and data regarding quantities

    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
    0:0.02
    1:0.13
    2:0.03
    3:0.10
    4:0.02
    5:0.07
    6:0.14
    7:0.02
    8:0.04
    9:0.28
    10:0.03
    11:0.05
    Negative Logits
    Stew
    -3.27
     Thames
    -3.15
     Stevens
    -3.07
     Goodwin
    -2.93
     DH
    -2.89
     Sussex
    -2.83
     Bow
    -2.81
     WD
    -2.81
    Wheel
    -2.79
     Ports
    -2.77
    POSITIVE LOGITS
     million
    4.49
    million
    3.87
     Million
    3.66
     MILL
    3.56
    mol
    3.53
     millions
    3.48
     Millions
    2.96
     MFT
    2.94
     mol
    2.93
     mil
    2.93
    Activations Density 0.013%

    No Known Activations