© 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. 11901
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns, particularly related to individuals and organizations

    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
    0:0.12
    1:0.30
    2:0.02
    3:0.03
    4:0.03
    5:0.02
    6:0.09
    7:0.09
    8:0.06
    9:0.03
    10:0.11
    11:0.04
    Negative Logits
     Ange
    -2.75
     Axel
    -2.72
     Alt
    -2.64
    Border
    -2.59
     Ci
    -2.54
     Cec
    -2.54
     ped
    -2.52
     Ig
    -2.52
     Suc
    -2.52
     Rox
    -2.52
    POSITIVE LOGITS
    man
    4.07
    MAN
    3.97
    Man
    3.50
    mans
    3.23
    MEN
    3.09
     Woman
    3.07
     Man
    3.05
    aman
    2.99
    lav
    2.89
    Men
    2.88
    Activations Density 0.008%

    No Known Activations