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. 8765
    Prev
    Next
    INDEX
    Explanations

    medical terms related to respiratory issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to respiratory illnesses and infections

    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
     Dinosaur
    -0.78
    ulously
    -0.76
    undo
    -0.72
     Mas
    -0.72
    inter
    -0.70
     Kin
    -0.68
     Deal
    -0.67
     corner
    -0.67
     Jud
    -0.66
     Tokens
    -0.66
    POSITIVE LOGITS
     pneumonia
    3.39
     respiratory
    2.53
     asthma
    2.08
     influenza
    2.08
     tuberculosis
    2.04
    pox
    2.01
     pneum
    1.97
     measles
    1.95
     cough
    1.91
     coughing
    1.72
    Activations Density 0.023%

    No Known Activations