© 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. 23271
    Prev
    Next
    INDEX
    Explanations

    statistical data and numerical information related to environmental and educational topics

    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
    0:0.03
    1:0.02
    2:0.03
    3:0.04
    4:0.05
    5:0.53
    6:0.03
    7:0.03
    8:0.02
    9:0.10
    10:0.02
    11:0.04
    Negative Logits
    advertisement
    -3.48
    Firstly
    -3.21
     VIDEOS
    -3.01
    ゴン
    -2.90
     lately
    -2.73
     externalToEVAOnly
    -2.73
    bnb
    -2.68
    artifacts
    -2.66
    JUST
    -2.58
     Flavoring
    -2.58
    POSITIVE LOGITS
     had
    4.35
     accounted
    3.42
     totaled
    3.29
    had
    3.29
     should
    3.14
     surpassed
    2.92
     outnumbered
    2.88
     must
    2.88
     SHALL
    2.86
     ought
    2.85
    Activations Density 0.088%

    No Known Activations