© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6608
    Prev
    Next
    INDEX
    Explanations

    closing braces and function end statements in code structures

    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
    1:0.06
    2:0.04
    3:0.05
    4:0.29
    5:0.05
    6:0.07
    7:0.09
    8:0.08
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
     Pledge
    -2.55
    EngineDebug
    -2.50
    irmation
    -2.44
     Prayer
    -2.37
     Savings
    -2.35
     Poe
    -2.28
     Preferred
    -2.27
     Quit
    -2.19
     Transition
    -2.18
    atron
    -2.17
    POSITIVE LOGITS
     EUR
    2.74
    !".
    2.61
    EEE
    2.58
    ��
    2.54
    IQ
    2.53
     Yugoslavia
    2.51
     Xie
    2.45
     Zamb
    2.44
    IUM
    2.40
    wana
    2.39
    Activations Density 0.003%

    No Known Activations