© 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. 6684
    Prev
    Next
    INDEX
    Explanations

    phrases relating to societal divisions and individual experiences

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.03
    3:0.05
    4:0.06
    5:0.50
    6:0.02
    7:0.03
    8:0.02
    9:0.14
    10:0.02
    11:0.03
    Negative Logits
     effortlessly
    -2.69
    etheless
    -2.66
    rive
    -2.61
    [/
    -2.54
    catentry
    -2.53
    Conclusion
    -2.48
    "?
    -2.46
    \"
    -2.44
    albeit
    -2.44
    "}
    -2.32
    POSITIVE LOGITS
     anymore
    3.53
     because
    3.03
    )—
    2.95
     unless
    2.88
     whichever
    2.77
    unless
    2.73
     any
    2.72
     if
    2.70
     anybody
    2.70
     either
    2.65
    Activations Density 0.187%

    No Known Activations