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. 1-RES-JB
    6. 6232
    Prev
    Next
    INDEX
    Explanations

    attributes of web elements or components

    oai_token-act-pair · gpt-3.5-turbo

    terms related to digital advertising formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mma
    -0.79
    rosso
    -0.77
    itability
    -0.75
    esta
    -0.74
    yah
    -0.72
    iyah
    -0.71
    aya
    -0.71
    loo
    -0.70
    wen
    -0.69
    iances
    -0.66
    POSITIVE LOGITS
    gallery
    0.74
     decorations
    0.73
    mast
    0.72
    rontal
    0.71
     exhibitions
    0.70
     Manson
    0.70
     aquarium
    0.69
     totem
    0.67
     decoration
    0.66
     pedest
    0.66
    Activations Density 0.037%

    No Known Activations