© 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. 4-RES-JB
    11. 6465
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions for recipes, particularly focusing on pork, beef, and potatoes

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and components used in cooking recipes

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

    No Comments

    Negative Logits
    agnetic
    -0.71
    vernment
    -0.70
    mson
    -0.68
    recated
    -0.67
     acron
    -0.66
    trained
    -0.65
    ospace
    -0.65
    essage
    -0.65
     staffed
    -0.62
     defect
    -0.62
    POSITIVE LOGITS
    Ingredients
    0.92
     recipes
    0.78
     flakes
    0.76
     recipe
    0.74
     Recipe
    0.74
    Kit
    0.73
     Ingredients
    0.73
     Soup
    0.72
     Cooking
    0.72
    fruit
    0.71
    Activations Density 0.095%

    No Known Activations