© 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. 23042
    Prev
    Next
    INDEX
    Explanations

    phrases and words that indicate opinions or attributions of meaning

    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
    0:0.19
    1:0.12
    2:0.06
    3:0.05
    4:0.03
    5:0.02
    6:0.07
    7:0.12
    8:0.02
    9:0.03
    10:0.18
    11:0.04
    Negative Logits
    inho
    -2.99
     Fuller
    -2.99
    ás
    -2.96
     Ramos
    -2.85
     裏覚醒
    -2.77
    ão
    -2.75
    ã
    -2.68
    iosyn
    -2.61
     Suarez
    -2.59
    Kelly
    -2.58
    POSITIVE LOGITS
     Mord
    9.06
     Morg
    5.50
     Rav
    4.05
     Saur
    3.58
     Nid
    3.55
     Malk
    3.50
     Hobbit
    3.44
     Nemesis
    3.41
     Vor
    3.39
     Tolkien
    3.23
    Activations Density 0.002%

    No Known Activations