© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12429
    Prev
    Next
    INDEX
    Explanations

    words related to fried food

    oai_token-act-pair · gpt-3.5-turbo

    references to fried food

    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
    QB
    -0.83
    Church
    -0.73
    agall
    -0.68
     Visitors
    -0.67
    Officers
    -0.66
    atican
    -0.65
    Org
    -0.63
     Percy
    -0.62
    patient
    -0.62
    女
    -0.61
    POSITIVE LOGITS
     fried
    1.39
     frying
    1.14
     fry
    1.07
     dough
    1.07
     cakes
    1.05
     tofu
    1.02
     crispy
    0.95
     eggs
    0.93
     pans
    0.93
     sauces
    0.92
    Activations Density 0.009%

    No Known Activations