© 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. 0-RES-JB
    11. 7604
    Prev
    Next
    INDEX
    Explanations

    adjectives related to health and weight

    oai_token-act-pair · gpt-3.5-turbo

    words related to health issues, especially concerning obesity and morbid conditions

    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
    apego
    -0.77
    ellation
    -0.76
    istle
    -0.70
     Remem
    -0.69
    Ä«
    -0.68
    yles
    -0.68
     Forth
    -0.66
     scapego
    -0.65
    AI
    -0.65
    gem
    -0.65
    POSITIVE LOGITS
     overweight
    2.90
     morbid
    2.63
     obese
    1.83
     uninsured
    1.18
     unhealthy
    1.10
     scrolling
    0.90
     frail
    0.88
     LDL
    0.88
     BMI
    0.85
     OP
    0.85
    Activations Density 0.038%

    No Known Activations