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. 0-RES-JB
    6. 8486
    Prev
    Next
    INDEX
    Explanations

    phrases related to different aspects of food like retrieval, inventory, processing, photography, and consumption

    oai_token-act-pair · gpt-3.5-turbo

    references to food-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tone
    -0.76
    linger
    -0.75
     Spectre
    -0.73
     Tempest
    -0.72
     Played
    -0.71
    edin
    -0.71
    yrights
    -0.70
     Reeves
    -0.70
     Studios
    -0.70
    mberg
    -0.68
    POSITIVE LOGITS
     food
    3.48
    food
    2.93
    Food
    2.79
     Food
    2.59
     foods
    2.51
     meals
    2.01
     meal
    1.92
     nutrition
    1.91
     culinary
    1.90
     cuisine
    1.85
    Activations Density 0.021%

    No Known Activations