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. 2-RES-JB
    6. 20443
    Prev
    Next
    INDEX
    Explanations

    different types of pasta

    oai_token-act-pair · gpt-3.5-turbo

    mentions of pasta and noodle-related dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elong
    -0.71
     Hamp
    -0.70
    sburg
    -0.69
    phas
    -0.68
     Ft
    -0.68
    izons
    -0.66
    affer
    -0.64
     Tall
    -0.63
    pher
    -0.62
    Reviewer
    -0.61
    POSITIVE LOGITS
     noodles
    1.15
     nood
    1.13
    arella
    1.03
     pasta
    1.01
     soup
    0.93
     spaghetti
    0.92
     seasoning
    0.84
     sauce
    0.83
     Soup
    0.82
    cake
    0.81
    Activations Density 0.008%

    No Known Activations