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. 4-RES-JB
    6. 5504
    Prev
    Next
    INDEX
    Explanations

    uses of commas in a series

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas in the text

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

    No Comments

    Negative Logits
     Horses
    -0.72
    Į
    -0.68
    orne
    -0.66
    Players
    -0.65
     Trouble
    -0.64
    quickShipAvailable
    -0.63
    ORS
    -0.63
    swick
    -0.61
     Companies
    -0.61
    obia
    -0.60
    POSITIVE LOGITS
     albeit
    1.03
    albeit
    0.77
     um
    0.77
    advant
    0.70
     inclusive
    0.69
    urban
    0.68
     uh
    0.67
     namely
    0.65
    burning
    0.64
    adic
    0.63
    Activations Density 0.326%

    No Known Activations