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. 9-RES-JB
    6. 782
    Prev
    Next
    INDEX
    Explanations

    information related to the field of medicine and medical practices

    oai_token-act-pair · gpt-3.5-turbo

    mentions of medicine and related fields or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sqor
    -0.80
    etime
    -0.73
    adia
    -0.72
    etheless
    -0.69
     Territories
    -0.66
     attm
    -0.65
     Podesta
    -0.63
    chrome
    -0.63
    flag
    -0.63
    icker
    -0.62
    POSITIVE LOGITS
     practitioner
    0.93
    utical
    0.89
    istry
    0.87
     prescribing
    0.85
    aceutical
    0.82
    utics
    0.80
     treating
    0.79
     practitioners
    0.78
    ogical
    0.77
     cures
    0.76
    Activations Density 0.039%

    No Known Activations