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. 8-RES-JB
    6. 5644
    Prev
    Next
    INDEX
    Explanations

    nutritional information, especially regarding protein, fats, and calories

    oai_token-act-pair · gpt-3.5-turbo

    nutritional information related to food, specifically macronutrients and calories

    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
     retrospective
    -0.79
    amera
    -0.77
    inqu
    -0.76
    Witness
    -0.74
    ovie
    -0.74
    USS
    -0.72
     arra
    -0.71
     Parade
    -0.71
    hunt
    -0.70
    computer
    -0.70
    POSITIVE LOGITS
     nutrients
    1.55
     carbohydrates
    1.45
     Protein
    1.43
     vitamins
    1.43
     calories
    1.38
     protein
    1.37
     fats
    1.37
     carbs
    1.35
     sugars
    1.34
     antioxidants
    1.33
    Activations Density 0.342%

    No Known Activations