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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14083
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, diseases, treatments, and studies

    oai_token-act-pair · gpt-3.5-turbo

    references to diseases and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.95
    onen
    -0.77
    nah
    -0.74
    hran
    -0.73
    ugi
    -0.73
    imar
    -0.72
    liam
    -0.72
    ón
    -0.71
    icz
    -0.71
    uj
    -0.70
    POSITIVE LOGITS
     Islands
    0.73
     Gate
    0.69
     Circle
    0.67
    Gate
    0.67
     Playoff
    0.65
     Logic
    0.65
     Heights
    0.64
     Bay
    0.59
     Institution
    0.58
     Oaks
    0.57
    Activations Density 0.330%

    No Known Activations