© 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. 11-RES-JB
    11. 7830
    Prev
    Next
    INDEX
    Explanations

    medical conditions related to the brain, such as Alzheimer's and Parkinson's disease

    oai_token-act-pair · gpt-3.5-turbo

    references to Alzheimer's and Parkinson's diseases along with related medical or scientific terms

    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
    cham
    -0.77
    nets
    -0.76
    eca
    -0.76
    nir
    -0.74
    mble
    -0.74
    */(
    -0.74
    alter
    -0.73
    lication
    -0.72
    umption
    -0.71
    HUD
    -0.69
    POSITIVE LOGITS
     Trophy
    0.80
     Park
    0.80
     Prize
    0.79
     Creed
    0.78
     Institution
    0.77
     Bros
    0.77
     Cell
    0.77
     Stones
    0.75
     Disease
    0.75
     Lect
    0.73
    Activations Density 0.152%

    No Known Activations