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. 8-RES-JB
    6. 8745
    Prev
    Next
    INDEX
    Explanations

    terms related to dietary experiments with specific components like fat, glucose, protein

    oai_token-act-pair · gpt-3.5-turbo

    content related to health and dietary studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.79
    redo
    -0.75
     escapes
    -0.69
     regrets
    -0.69
     sooner
    -0.67
     EntityItem
    -0.67
     hurts
    -0.65
    Things
    -0.64
     endif
    -0.63
    tis
    -0.63
    POSITIVE LOGITS
     randomized
    1.12
     randomly
    1.11
     Experiment
    1.09
     experiment
    1.07
     simulated
    1.05
     Participants
    1.01
     participants
    0.99
     questionnaire
    0.97
     Subjects
    0.95
     placebo
    0.95
    Activations Density 0.534%

    No Known Activations