© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 9438
    Prev
    Next
    INDEX
    Explanations

    words related to medical patients or healthcare contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to patients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angular
    -0.82
    OPA
    -0.76
    oras
    -0.72
    ãĥ©ãĥ³
    -0.70
    argon
    -0.69
    ordan
    -0.69
    gers
    -0.68
     Dunk
    -0.68
    ball
    -0.65
     Montana
    -0.64
    POSITIVE LOGITS
     patients
    1.03
     patient
    0.97
     Patients
    0.94
    ients
    0.93
     diagnosed
    0.89
     hospitalized
    0.89
    killer
    0.85
    ysis
    0.85
     suffering
    0.85
     undergoing
    0.83
    Activations Density 0.036%

    No Known Activations