© 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. 17328
    Prev
    Next
    INDEX
    Explanations

    the letter "D" with high prominence

    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
    0:0.08
    1:0.08
    2:0.08
    3:0.08
    4:0.07
    5:0.08
    6:0.07
    7:0.08
    8:0.08
    9:0.09
    10:0.08
    11:0.08
    Negative Logits
    taboola
    -3.25
    ADVERTISEMENT
    -3.01
    edin
    -2.83
    Atl
    -2.74
    abad
    -2.71
    Pir
    -2.70
    notation
    -2.64
    Gordon
    -2.55
    AAA
    -2.55
     ­
    -2.55
    POSITIVE LOGITS
     bitch
    3.08
     whine
    3.01
     Cooke
    2.97
     Winchester
    2.73
     insure
    2.71
     warr
    2.69
     negro
    2.66
     exhaust
    2.55
     wills
    2.53
     SSD
    2.51
    Activations Density 0.000%

    No Known Activations