© 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. 5209
    Prev
    Next
    INDEX
    Explanations

    names of political figures and individuals related to political events

    oai_token-act-pair · gpt-3.5-turbo
    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
    0:0.29
    1:0.04
    2:0.06
    3:0.02
    4:0.09
    5:0.07
    6:0.10
    7:0.04
    8:0.03
    9:0.03
    10:0.12
    11:0.04
    Negative Logits
    itial
    -1.31
     relegation
    -1.28
    Interstitial
    -1.28
    aughtered
    -1.26
    Liter
    -1.26
    emonium
    -1.25
     Bengal
    -1.25
    mingham
    -1.25
     Hung
    -1.23
     Gleaming
    -1.21
    POSITIVE LOGITS
    OTUS
    1.49
    gur
    1.34
     manip
    1.33
    uchin
    1.31
    DonaldTrump
    1.23
    obby
    1.17
     already
    1.15
     memos
    1.15
     disguised
    1.13
    bryce
    1.12
    Activations Density 0.018%

    No Known Activations