© 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. 5578
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and data manipulation

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.09
    1:0.08
    2:0.06
    3:0.13
    4:0.04
    5:0.09
    6:0.05
    7:0.17
    8:0.05
    9:0.04
    10:0.03
    11:0.11
    Negative Logits
    abwe
    -1.92
     accur
    -1.89
     yourselves
    -1.87
     PCR
    -1.87
     Jihad
    -1.85
    hovah
    -1.84
    anwhile
    -1.83
     Witches
    -1.81
     Solitaire
    -1.81
     Gö
    -1.78
    POSITIVE LOGITS
    Icon
    2.58
    status
    2.53
    title
    2.37
    Title
    2.33
     title
    2.29
    FontSize
    2.23
    });
    2.21
    format
    2.19
     icon
    2.18
    desktop
    2.18
    Activations Density 0.020%

    No Known Activations