© 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 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. 13041
    Prev
    Next
    INDEX
    Explanations

    references to agencies and organizations involved in regulatory and enforcement activities

    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
    1:0.03
    2:0.04
    3:0.04
    4:0.05
    5:0.09
    6:0.03
    7:0.05
    8:0.07
    9:0.03
    10:0.04
    11:0.46
    Negative Logits
     ['
    -3.64
    ');
    -3.44
    ').
    -3.29
    '),
    -3.20
    ',"
    -3.06
    ',
    -3.02
    ':
    -2.93
     recogn
    -2.86
    SPONSORED
    -2.79
    '.
    -2.75
    POSITIVE LOGITS
    .(
    4.23
    (
    3.67
    .—
    3.46
     "(
    3.24
    ^^
    3.18
    !
    3.16
    ."
    3.12
    ((
    3.03
    ●
    3.03
     ---
    3.00
    Activations Density 0.002%

    No Known Activations