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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22233
    Prev
    Next
    INDEX
    Explanations

    high-protein or specific nutrition-related terms, specifically related to the ketogenic diet

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ketogenic diet and low-carb diets

    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
    cens
    -0.86
     Moff
    -0.83
     Shore
    -0.81
    女
    -0.79
     Heard
    -0.77
    rio
    -0.75
     Tacoma
    -0.74
     Crane
    -0.73
     Citizenship
    -0.72
    Guard
    -0.71
    POSITIVE LOGITS
     carb
    2.72
     ket
    2.64
    ket
    2.57
     carbs
    2.34
    carb
    2.29
     Carb
    2.05
     Ket
    2.05
     insulin
    2.01
     carbohydrates
    1.91
     glucose
    1.87
    Activations Density 0.052%

    No Known Activations