© 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. 18139
    Prev
    Next
    INDEX
    Explanations

    medical conditions, specifically Parkinson's disease and multiple sclerosis

    oai_token-act-pair · gpt-3.5-turbo

    references to neurological and medical conditions

    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
     Hanna
    -0.80
     Terra
    -0.72
    Sab
    -0.70
     boiler
    -0.68
    į
    -0.67
    Tex
    -0.67
     Kel
    -0.65
     Avatar
    -0.65
    Cu
    -0.64
     Enc
    -0.64
    POSITIVE LOGITS
     Parkinson
    3.31
     dementia
    2.14
     Alzheimer
    2.14
     epilepsy
    2.06
     sclerosis
    1.98
     ALS
    1.86
     arthritis
    1.81
     epile
    1.67
     prostate
    1.65
     schizophrenia
    1.61
    Activations Density 0.047%

    No Known Activations