© 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. 6875
    Prev
    Next
    INDEX
    Explanations

    references to authors and their literary style

    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
    0:0.21
    1:0.09
    2:0.08
    3:0.05
    4:0.07
    5:0.03
    6:0.07
    7:0.08
    8:0.04
    9:0.04
    10:0.09
    11:0.10
    Negative Logits
     Mald
    -4.12
     Bunker
    -3.28
     Bangl
    -3.25
     Valkyrie
    -3.06
     Corm
    -3.03
     Rio
    -3.01
     Murphy
    -2.96
     Weld
    -2.94
     McAuliffe
    -2.91
    dies
    -2.84
    POSITIVE LOGITS
     styl
    7.34
     Kanye
    4.52
     salon
    4.13
    Sty
    3.98
     Kardashian
    3.77
     Staples
    3.67
     hairst
    3.57
     plagiar
    3.55
     dermat
    3.53
     iPod
    3.43
    Activations Density 0.000%

    No Known Activations