© 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. 14511
    Prev
    Next
    INDEX
    Explanations

    titles of movies or TV shows

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

    elements of film and music history

    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
    0:0.04
    1:0.05
    2:0.08
    3:0.03
    4:0.05
    5:0.10
    6:0.12
    7:0.17
    8:0.08
    9:0.04
    10:0.12
    11:0.06
    Negative Logits
    ordinary
    -1.35
    pection
    -1.34
    erity
    -1.30
    acent
    -1.29
    estate
    -1.21
     bud
    -1.19
     complying
    -1.17
     depends
    -1.16
     wiser
    -1.15
    \-
    -1.14
    POSITIVE LOGITS
     Remix
    1.59
     anthology
    1.50
     starring
    1.43
     Rivals
    1.42
     Seasons
    1.39
    Teen
    1.22
     MTV
    1.21
    Season
    1.21
    Interstitial
    1.19
     Nemesis
    1.18
    Activations Density 0.239%

    No Known Activations