Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 3914
    Prev
    Next
    INDEX
    Explanations

    references to holidays, especially Christmas, and associated traditions, sentiments, and controversies

    oai_token-act-pair · gpt-3.5-turbo

    themes related to the celebration and traditions of Christmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qus
    -0.82
     refuted
    -0.82
    ysis
    -0.76
    Voice
    -0.76
    peer
    -0.76
    asive
    -0.76
     penetration
    -0.76
    imeter
    -0.75
     deposition
    -0.74
     takedown
    -0.73
    POSITIVE LOGITS
     festive
    1.93
     holiday
    1.83
     holidays
    1.79
     festivities
    1.78
    Christmas
    1.70
    holiday
    1.69
     Christmas
    1.69
     celebrations
    1.67
     Holiday
    1.66
     celebration
    1.64
    Activations Density 0.700%

    No Known Activations