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. 0-RES-JB
    6. 3712
    Prev
    Next
    INDEX
    Explanations

    smells or odors in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to unpleasant or notable smells

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilee
    -0.71
     Answers
    -0.71
     Conversion
    -0.67
     engagements
    -0.67
    Program
    -0.66
    hips
    -0.65
     Credits
    -0.63
    program
    -0.62
    625
    -0.61
    ford
    -0.61
    POSITIVE LOGITS
     smell
    4.02
     smells
    2.98
     smelled
    2.84
     smelling
    2.75
     scent
    2.72
     odor
    2.70
     aroma
    2.39
     fragrance
    2.02
     stink
    1.93
     taste
    1.80
    Activations Density 0.031%

    No Known Activations