© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 24013
    Prev
    Next
    INDEX
    Explanations

    mentions of medical patients and treatments

    oai_token-act-pair · gpt-3.5-turbo

    references to patients in a medical context

    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
    angular
    -0.75
    argon
    -0.73
    oras
    -0.71
     Dunk
    -0.69
    dated
    -0.67
    OPA
    -0.66
    gers
    -0.66
    å°Ĩ
    -0.65
    shock
    -0.65
    dust
    -0.65
    POSITIVE LOGITS
     patients
    1.01
     patient
    0.93
     hospitalized
    0.90
    ients
    0.88
     Patients
    0.88
     suffering
    0.87
     diagnosed
    0.85
    ysis
    0.83
    ele
    0.82
     care
    0.82
    Activations Density 0.043%

    No Known Activations