© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 9627
    Prev
    Next
    INDEX
    Explanations

    references to the term "Santa" and Christmas-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to gift-giving and Secret Santa events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bleacher
    -0.77
     rooft
    -0.70
     jets
    -0.65
    undo
    -0.65
    ihadi
    -0.63
     Nanto
    -0.63
    arbon
    -0.63
    kil
    -0.63
    ault
    -0.63
    inki
    -0.62
    POSITIVE LOGITS
     gift
    0.97
     Geek
    0.97
    etsy
    0.93
     Gifts
    0.89
    Santa
    0.89
     gifts
    0.88
     Santa
    0.85
     Gift
    0.83
    nesday
    0.82
    !!!!
    0.80
    Activations Density 0.129%

    No Known Activations