© 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. 4-RES-JB
    11. 10542
    Prev
    Next
    INDEX
    Explanations

    terms related to specific dietary approaches, such as low-carb, vegan, paleo, and ketogenic diets

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to diet and nutrition

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

    No Comments

    Negative Logits
     Hirosh
    -0.77
     Kissinger
    -0.77
     Snowden
    -0.76
     Scalia
    -0.76
     Lange
    -0.75
     trespass
    -0.72
     SX
    -0.71
     treaties
    -0.70
     CCTV
    -0.70
     towed
    -0.70
    POSITIVE LOGITS
    rition
    1.15
     lifestyle
    1.05
    estead
    0.99
    ritional
    0.95
     carbohyd
    0.90
    ifestyle
    0.87
    utical
    0.87
    Nut
    0.87
    onut
    0.86
     Fitness
    0.86
    Activations Density 0.481%

    No Known Activations