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. 8-RES-JB
    6. 8708
    Prev
    Next
    INDEX
    Explanations

    terms related to occasions or events of joy, celebration, or festivities

    oai_token-act-pair · gpt-3.5-turbo

    the act of celebrating or references to ceremonies and festivities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 8 - joy

    No Comments

    Negative Logits
    abases
    -0.76
    nih
    -0.73
    æ©Ł
    -0.70
    iban
    -0.66
    ridge
    -0.66
    say
    -0.65
    ãĥĥãĥī
    -0.65
     scanner
    -0.64
    seed
    -0.64
    uci
    -0.64
    POSITIVE LOGITS
     holidays
    0.95
     celebrations
    0.95
     celebrating
    0.93
    issance
    0.82
     Celebr
    0.79
     Celebration
    0.78
    noon
    0.78
     birthday
    0.77
     Thanksgiving
    0.76
     honoring
    0.76
    Activations Density 0.055%

    No Known Activations