© 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. 10-ATT-KK
    11. 12233
    Prev
    Next
    INDEX
    Explanations

    instances of reported actions or events related to claims or allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.08
    2:0.14
    3:0.04
    4:0.03
    5:0.01
    6:0.14
    7:0.09
    8:0.03
    9:0.04
    10:0.18
    11:0.05
    Negative Logits
     Guam
    -3.45
     PJ
    -3.22
    ł
    -3.09
     Giuliani
    -3.04
     chi
    -2.89
     Jacobs
    -2.87
     McInt
    -2.71
    igl
    -2.67
     Jacksonville
    -2.65
     DP
    -2.54
    POSITIVE LOGITS
     Sale
    7.75
    sale
    4.16
     Sales
    3.94
     SAL
    3.57
    Sales
    3.40
     Coup
    3.35
     Selling
    3.31
     Sold
    3.29
     sale
    3.28
    Sold
    3.18
    Activations Density 0.001%

    No Known Activations