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. 0-RES-JB
    6. 259
    Prev
    Next
    INDEX
    Explanations

    mentions of vitamins and nutrients in relation to food or health

    oai_token-act-pair · gpt-3.5-turbo

    references to vitamins and nutrients in the context of health and diet

    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
    glers
    -0.69
    Gate
    -0.67
     Inferno
    -0.66
    gha
    -0.66
     Barker
    -0.65
     Chambers
    -0.64
    ateurs
    -0.63
     Walls
    -0.63
    Ba
    -0.63
     dispatch
    -0.62
    POSITIVE LOGITS
     vitamins
    3.03
     vitamin
    2.89
     Vitamin
    2.45
     nutrient
    2.29
     nutrients
    2.15
     nutritional
    2.15
    itamin
    2.04
    amins
    1.82
     nutrition
    1.66
     antioxidants
    1.59
    Activations Density 0.028%

    No Known Activations