© 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. 17169
    Prev
    Next
    INDEX
    Explanations

    words related to belief, accountability, and consequences in interpersonal or societal contexts

    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
    0:0.03
    1:0.04
    2:0.06
    3:0.06
    4:0.10
    5:0.09
    6:0.04
    7:0.08
    8:0.05
    9:0.29
    10:0.03
    11:0.07
    Negative Logits
     Horses
    -2.61
    kids
    -2.56
    osaurs
    -2.53
    veyard
    -2.47
     Beaut
    -2.42
     Leban
    -2.40
     Skies
    -2.37
    Scroll
    -2.35
    oos
    -2.34
     Tories
    -2.29
    POSITIVE LOGITS
     his
    3.46
     himself
    3.40
     thereby
    3.11
     whom
    3.05
     acquaintance
    3.03
     he
    2.95
     defendant
    2.95
     circumstance
    2.94
     lawfully
    2.93
     him
    2.89
    Activations Density 0.603%

    No Known Activations