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. 6-RES-JB
    6. 10447
    Prev
    Next
    INDEX
    Explanations

    recipes or information related to cooking with curry as a key ingredient

    oai_token-act-pair · gpt-3.5-turbo

    references to curry dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Armory
    -0.79
    weeney
    -0.78
    izons
    -0.76
    igue
    -0.76
    ively
    -0.75
    olver
    -0.75
    omething
    -0.72
    swick
    -0.71
    oenix
    -0.71
     Mayhem
    -0.70
    POSITIVE LOGITS
    rer
    0.89
    rers
    0.83
    hyde
    0.77
    bris
    0.75
     versa
    0.72
    istani
    0.71
    bye
    0.70
    Ped
    0.69
    dry
    0.68
     curry
    0.68
    Activations Density 0.043%

    No Known Activations