© 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. 14227
    Prev
    Next
    INDEX
    Explanations

    descriptions of people dressing up in various costumes

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

    instances of dressing up or wearing costumes in various contexts

    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
    0:0.01
    1:0.02
    2:0.08
    3:0.08
    4:0.01
    5:0.05
    6:0.05
    7:0.11
    8:0.09
    9:0.30
    10:0.05
    11:0.09
    Negative Logits
    lisher
    -1.42
    akings
    -1.31
     contribut
    -1.29
     Areas
    -1.25
    thing
    -1.21
     Publishing
    -1.18
     Publishers
    -1.16
     widened
    -1.16
    Parts
    -1.15
    published
    -1.13
    POSITIVE LOGITS
     stereotypical
    1.57
     faux
    1.49
     ballet
    1.26
     stereotyp
    1.26
     toile
    1.23
     casually
    1.21
     dign
    1.19
    AME
    1.18
     draped
    1.18
     Lego
    1.16
    Activations Density 0.014%

    No Known Activations