© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 40148
    Prev
    Next
    INDEX
    Explanations

    mentions of Santa and associated gift-giving themes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.05
    3:0.05
    4:0.04
    5:0.05
    6:0.03
    7:0.04
    8:0.02
    9:0.06
    10:0.18
    11:0.40
    Negative Logits
     Gifts
    -2.16
     birthday
    -2.06
     gif
    -2.05
    endars
    -2.03
     gift
    -2.03
     gifts
    -1.99
     Hermes
    -1.97
    Christmas
    -1.94
     kindness
    -1.93
     Gift
    -1.91
    POSITIVE LOGITS
    itri
    1.85
    SPONSORED
    1.81
     fracturing
    1.78
     Ing
    1.75
     Controlled
    1.73
     inexperienced
    1.65
    ofer
    1.63
    ワン
    1.61
     Kut
    1.59
    isky
    1.58
    Activations Density 0.007%

    No Known Activations