© 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. 5-ATT-KK
    11. 39741
    Prev
    Next
    INDEX
    Explanations

    references to specific holidays and celebrations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.13
    2:0.03
    3:0.05
    4:0.05
    5:0.33
    6:0.04
    7:0.02
    8:0.05
    9:0.06
    10:0.09
    11:0.06
    Negative Logits
    ワン
    -2.00
    KI
    -1.84
    rolet
    -1.82
    ilk
    -1.76
    Struct
    -1.74
     Vander
    -1.73
     CK
    -1.70
    orea
    -1.69
    POR
    -1.68
    KN
    -1.67
    POSITIVE LOGITS
    iversary
    1.89
     Day
    1.83
     Month
    1.66
     blackout
    1.61
     Celebration
    1.59
     safely
    1.59
    eday
    1.58
     dinners
    1.58
     Yiannopoulos
    1.56
     etiquette
    1.56
    Activations Density 0.003%

    No Known Activations