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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7594
    Prev
    Next
    INDEX
    Explanations

    mentions of neurodegenerative diseases and related medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    medical conditions, particularly Alzheimer's and Parkinson's disease

    oai_token-act-pair · gpt-3.5-turbo
    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
    76561
    -0.83
    soDeliveryDate
    -0.81
    ellation
    -0.76
     Zoro
    -0.76
    =#
    -0.71
    hops
    -0.68
    DJ
    -0.67
    ILE
    -0.65
     Pixie
    -0.64
    )=(
    -0.64
    POSITIVE LOGITS
     disease
    1.03
     Disease
    0.99
     Alzheimer
    0.98
     dementia
    0.95
    clerosis
    0.89
    iac
    0.86
     plaque
    0.81
    etics
    0.79
     dement
    0.76
     diagnosis
    0.75
    Activations Density 0.024%

    No Known Activations