© 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. 1-RES-JB
    11. 6428
    Prev
    Next
    INDEX
    Explanations

    mentions of the medical condition "diabetes."

    oai_token-act-pair · gpt-3.5-turbo

    references to diabetes and related health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AW
    -0.75
    Sources
    -0.74
    INGS
    -0.72
    и
    -0.69
    rd
    -0.68
    awatts
    -0.68
    source
    -0.68
    pheus
    -0.67
     WARN
    -0.66
    âĻ¦
    -0.65
    POSITIVE LOGITS
     mell
    1.40
     diabetes
    1.06
     Diabetes
    0.91
    abetes
    0.89
     complications
    0.88
     glucose
    0.86
    esity
    0.85
     obesity
    0.83
     ket
    0.82
     insulin
    0.82
    Activations Density 0.007%

    No Known Activations