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. 10-RES-JB
    6. 21066
    Prev
    Next
    INDEX
    Explanations

    details related to nutritional information like protein, fats, carbohydrates, and vitamins

    oai_token-act-pair · gpt-3.5-turbo

    nutritional information and measurements related to food components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kafka
    -0.86
    criminal
    -0.79
     retrospective
    -0.77
     vandal
    -0.74
     taxi
    -0.73
     dolls
    -0.73
    computer
    -0.71
     taxis
    -0.71
     Camer
    -0.71
    ionage
    -0.70
    POSITIVE LOGITS
     carbohydrates
    1.70
     antioxidants
    1.63
     nutrients
    1.59
     fats
    1.57
     vitamins
    1.56
     carbs
    1.55
     protein
    1.54
     carbohydrate
    1.54
     Protein
    1.50
     calories
    1.49
    Activations Density 0.254%

    No Known Activations