© 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. 12651
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to notable figures or institutions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to individuals named Janet and various related names

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.05
    2:0.07
    3:0.15
    4:0.02
    5:0.03
    6:0.14
    7:0.12
    8:0.05
    9:0.12
    10:0.09
    11:0.08
    Negative Logits
     Reson
    -1.18
     marrow
    -1.08
    xp
    -1.00
     dig
    -0.97
     ans
    -0.95
     Emin
    -0.95
     thirsty
    -0.94
    ⓘ
    -0.93
    thodox
    -0.92
    hematic
    -0.92
    POSITIVE LOGITS
     Baird
    1.31
    kefeller
    1.22
    heid
    1.19
    bush
    1.15
    acy
    1.14
    iffe
    1.13
    rate
    1.13
    mare
    1.12
    lish
    1.11
    amar
    1.10
    Activations Density 0.001%

    No Known Activations