© 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. 5242
    Prev
    Next
    INDEX
    Explanations

    words related to holidays, specifically Christmas

    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
    0:0.39
    1:0.03
    2:0.03
    3:0.02
    4:0.04
    5:0.05
    6:0.10
    7:0.06
    8:0.03
    9:0.04
    10:0.11
    11:0.05
    Negative Logits
    ancial
    -1.71
    oxin
    -1.57
    trl
    -1.53
     fielded
    -1.52
    lation
    -1.49
    ursive
    -1.48
    idespread
    -1.48
    animous
    -1.46
    insk
    -1.39
    lations
    -1.36
    POSITIVE LOGITS
     pageant
    1.58
     lovers
    1.54
     amen
    1.53
    goers
    1.51
     shoppers
    1.47
     Solitaire
    1.46
    birth
    1.46
     Anniversary
    1.41
    ��
    1.40
     bachelor
    1.39
    Activations Density 0.077%

    No Known Activations