© 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. 3-RES-JB
    11. 584
    Prev
    Next
    INDEX
    Explanations

    references to pie

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances of the word "pie."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spring
    -0.80
    iveness
    -0.75
     Students
    -0.73
     EDITION
    -0.70
    runners
    -0.70
     Examiner
    -0.70
    nen
    -0.68
    nesses
    -0.67
    sers
    -0.66
    iqueness
    -0.64
    POSITIVE LOGITS
     pie
    1.30
     pies
    1.24
    pie
    1.09
     Pie
    0.98
    Pie
    0.96
     crust
    0.91
     desserts
    0.89
    artisan
    0.83
    ced
    0.82
     dough
    0.80
    Activations Density 0.013%

    No Known Activations