© 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. 0-RES-JB
    11. 19019
    Prev
    Next
    INDEX
    Explanations

    keywords related to Alzheimer's disease and dementia

    oai_token-act-pair · gpt-3.5-turbo

    terms related to Alzheimer's disease and dementia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whatsoever
    -0.66
    ube
    -0.66
     rigging
    -0.63
     pole
    -0.63
     exchanges
    -0.62
    ope
    -0.62
     SUP
    -0.61
     prop
    -0.61
     floats
    -0.61
     bolt
    -0.61
    POSITIVE LOGITS
     Alzheimer
    3.80
     dementia
    2.41
     Parkinson
    2.13
     Alz
    1.96
     ALS
    1.75
     Autism
    1.58
     Lyme
    1.47
     Canaver
    1.46
     Diabetes
    1.46
     autism
    1.37
    Activations Density 0.014%

    No Known Activations