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. 17217
    Prev
    Next
    INDEX
    Explanations

    mentions of the medical condition Multiple Sclerosis (MS) and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to multiple sclerosis (MS)

    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
     carrot
    -0.86
     carrots
    -0.74
    ¨
    -0.73
    ı
    -0.73
    abbit
    -0.70
    ulhu
    -0.69
    opian
    -0.69
    hovah
    -0.69
    arov
    -0.67
    ollow
    -0.65
    POSITIVE LOGITS
     MS
    3.92
    MS
    2.21
     ms
    1.60
     MD
    1.33
     BS
    1.33
     MR
    1.28
     Spartans
    1.28
     MN
    1.23
     MSI
    1.19
     ALS
    1.19
    Activations Density 0.015%

    No Known Activations