© 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. 11-RES-JB
    11. 7545
    Prev
    Next
    INDEX
    Explanations

    words related to health and healthcare

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to health-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BU
    -0.74
    hops
    -0.73
    isu
    -0.72
    aturday
    -0.64
    ezvous
    -0.63
     Kinnikuman
    -0.63
    sth
    -0.63
    ittal
    -0.62
     Column
    -0.61
     Ort
    -0.61
    POSITIVE LOGITS
     wellness
    1.23
     wellbeing
    1.20
     safety
    1.15
     nutrition
    1.02
     welfare
    1.02
     fitness
    0.99
     disability
    0.99
    safety
    0.96
     hygiene
    0.94
     Welfare
    0.94
    Activations Density 0.075%

    No Known Activations