© 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. 24127
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence structure elements

    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
    0:0.07
    1:0.02
    2:0.06
    3:0.04
    4:0.06
    5:0.04
    6:0.30
    7:0.03
    8:0.07
    9:0.18
    10:0.03
    11:0.03
    Negative Logits
    erker
    -4.29
    hovah
    -4.05
     transmitter
    -3.73
    halla
    -3.65
     lig
    -3.51
     CFL
    -3.50
     flu
    -3.47
     McCabe
    -3.41
     transmit
    -3.37
    ゴン
    -3.36
    POSITIVE LOGITS
    Sand
    11.03
     Sand
    10.15
    sand
    8.49
     sand
    7.59
     Sands
    6.10
     sands
    5.32
     Sed
    4.75
    Rock
    4.71
     sandbox
    4.62
     sandy
    4.49
    Activations Density 0.012%

    No Known Activations