© 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. 4-RES-JB
    11. 22001
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and treatments, specifically focusing on epilepsy

    oai_token-act-pair · gpt-3.5-turbo

    words related to medical and biological contexts

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

    No Comments

    Negative Logits
    ĸļ
    -0.94
    iversal
    -0.91
    ortium
    -0.87
    axter
    -0.85
    aido
    -0.82
    icum
    -0.80
    etheless
    -0.79
    icter
    -0.79
    esson
    -0.79
    olver
    -0.79
    POSITIVE LOGITS
    mma
    0.92
    tto
    0.90
    ttes
    0.81
    gged
    0.78
    tta
    0.77
    tsky
    0.75
    zza
    0.73
    gging
    0.72
    tt
    0.71
     paths
    0.70
    Activations Density 0.014%

    No Known Activations