© 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. 17768
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the."

    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
    0:0.10
    1:0.03
    2:0.09
    3:0.05
    4:0.06
    5:0.04
    6:0.17
    7:0.04
    8:0.13
    9:0.15
    10:0.04
    11:0.05
    Negative Logits
     Taj
    -4.70
    rig
    -3.99
     Robbins
    -3.87
     Saud
    -3.71
     Debbie
    -3.65
     Dodd
    -3.62
     inn
    -3.52
     embro
    -3.31
     Lynd
    -3.31
     Derrick
    -3.31
    POSITIVE LOGITS
     Plasma
    10.32
     plasma
    8.05
    asma
    5.72
     KDE
    5.49
     Ion
    4.18
     Xen
    3.96
     Velocity
    3.89
     Xperia
    3.85
     Atom
    3.84
     Radiation
    3.83
    Activations Density 0.000%

    No Known Activations