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. 20372
    Prev
    Next
    INDEX
    Explanations

    phrases related to various illnesses and medical conditions, with a focus on cancer

    oai_token-act-pair · gpt-3.5-turbo

    topics related to illness and medical conditions

    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
    ramid
    -0.85
    soDeliveryDate
    -0.71
    xtap
    -0.70
    semble
    -0.67
     Tables
    -0.66
     Zup
    -0.65
    values
    -0.63
    WT
    -0.63
     prim
    -0.62
     Figures
    -0.61
    POSITIVE LOGITS
     diagnosed
    1.22
     ailments
    1.14
     diagnosis
    1.07
     illness
    1.07
     diagnoses
    1.06
     medication
    1.04
    Doctors
    1.02
     pneumonia
    1.01
     ail
    1.01
     remission
    1.00
    Activations Density 0.233%

    No Known Activations