© 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. 3-ATT-KK
    11. 14193
    Prev
    Next
    INDEX
    Explanations

    phrases related to gender roles and workplace dynamics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    advice or instructions related to personal relationships and self-care

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.10
    2:0.08
    3:0.03
    4:0.07
    5:0.14
    6:0.11
    7:0.07
    8:0.07
    9:0.06
    10:0.12
    11:0.06
    Negative Logits
     disag
    -1.55
    terday
    -1.54
     Syri
    -1.41
    lier
    -1.38
    was
    -1.38
    lihood
    -1.33
     appell
    -1.33
     politic
    -1.31
     unanimous
    -1.28
     derog
    -1.26
    POSITIVE LOGITS
    ーテ
    1.41
    avascript
    1.38
    amara
    1.32
    iculty
    1.31
    setup
    1.30
    ビ
    1.29
    アル
    1.27
     bondage
    1.25
    り
    1.24
    idth
    1.23
    Activations Density 0.653%

    No Known Activations