© 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. 11-RES-JB
    11. 20508
    Prev
    Next
    INDEX
    Explanations

    nutritional information related to food items

    oai_token-act-pair · gpt-3.5-turbo

    nutritional information, particularly quantities of calories, fats, carbohydrates, and proteins

    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
     collectors
    -0.79
    ionage
    -0.73
     sweeps
    -0.70
     Inspector
    -0.69
     Lovecraft
    -0.69
     Pinball
    -0.67
    inqu
    -0.67
    OPLE
    -0.66
     seism
    -0.66
     excav
    -0.66
    POSITIVE LOGITS
     carbs
    1.81
     carbohydrates
    1.66
     carbohydrate
    1.58
     fats
    1.50
     Protein
    1.48
     calories
    1.48
     protein
    1.42
     Calories
    1.42
     fat
    1.41
     sugars
    1.36
    Activations Density 0.161%

    No Known Activations