© 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. 8-RES-JB
    11. 17800
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "pizza" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to pizza

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itud
    -0.80
    lasses
    -0.79
    hips
    -0.78
    uate
    -0.77
    Thom
    -0.77
    track
    -0.71
    uating
    -0.71
    ought
    -0.68
    ARB
    -0.68
    ility
    -0.67
    POSITIVE LOGITS
     dough
    1.04
     crust
    1.02
     oven
    0.96
     Hut
    0.92
     Dough
    0.90
     pies
    0.87
     delivery
    0.85
     pizza
    0.84
    ocalypse
    0.83
    isine
    0.83
    Activations Density 0.028%

    No Known Activations