© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21055
    Prev
    Next
    INDEX
    Explanations

    nutritional advice related to diet and food components

    oai_token-act-pair · gpt-3.5-turbo

    nutritional components and dietary recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrights
    -0.90
    ionage
    -0.83
     seism
    -0.80
     DMCA
    -0.73
    Intern
    -0.72
     scrut
    -0.72
     bidding
    -0.71
    ayson
    -0.70
     Pinball
    -0.70
     espionage
    -0.69
    POSITIVE LOGITS
     foods
    1.72
     carbohydrates
    1.69
     carbs
    1.68
     diets
    1.62
     diet
    1.57
     carbohydrate
    1.55
     meals
    1.50
     fats
    1.46
     dietary
    1.44
     vegetables
    1.43
    Activations Density 0.358%

    No Known Activations