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. 14318
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific ingredients used in cooking

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ingredients in food or recipes

    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
    zik
    -0.78
    graph
    -0.64
     III
    -0.63
     Dot
    -0.62
    lance
    -0.62
    ower
    -0.61
    Wide
    -0.61
     II
    -0.60
     Jub
    -0.59
     VI
    -0.59
    POSITIVE LOGITS
     ingredients
    3.72
     ingredient
    2.92
     ingred
    2.36
     Ingredients
    2.33
    Ingredients
    2.29
    redients
    2.11
     recipes
    1.72
     additives
    1.66
     spices
    1.61
     herbs
    1.53
    Activations Density 0.016%

    No Known Activations