© 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. 3-RES-JB
    11. 7273
    Prev
    Next
    INDEX
    Explanations

    phrases related to existing or pre-existing conditions in the context of healthcare

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms related to pre-existing health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orious
    -0.78
    ogy
    -0.73
    mable
    -0.68
     Osaka
    -0.62
    umen
    -0.62
    err
    -0.61
    son
    -0.60
    achi
    -0.59
    cellence
    -0.58
    SEE
    -0.57
    POSITIVE LOGITS
    existing
    1.00
     pree
    0.82
    entials
    0.78
    foundland
    0.77
     conditions
    0.77
     Conditions
    0.75
    nesses
    0.72
     arrangements
    0.72
    querque
    0.71
     disorders
    0.68
    Activations Density 0.011%

    No Known Activations