© 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. 6566
    Prev
    Next
    INDEX
    Explanations

    references to technology and its impact on society

    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
    2:0.06
    3:0.04
    4:0.05
    5:0.33
    6:0.02
    7:0.04
    8:0.02
    9:0.28
    10:0.02
    11:0.05
    Negative Logits
    版
    -3.07
     awaited
    -2.89
    Updated
    -2.58
     remained
    -2.48
    王
    -2.36
    ITED
    -2.34
    orted
    -2.33
    urers
    -2.32
    arios
    -2.29
    aires
    -2.27
    POSITIVE LOGITS
     you
    2.93
     somebody
    2.92
     it
    2.91
     someone
    2.89
     something
    2.78
     or
    2.70
     accidentally
    2.70
    *,
    2.67
    someone
    2.63
     your
    2.50
    Activations Density 0.313%

    No Known Activations