© 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. 11998
    Prev
    Next
    INDEX
    Explanations

    words related to biology and medical studies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biology and specifically various fields of biological study

    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
     floats
    -0.70
     unw
    -0.69
     char
    -0.68
     tight
    -0.67
     floating
    -0.64
     aff
    -0.64
     passing
    -0.61
     wheel
    -0.61
     dist
    -0.61
     cash
    -0.60
    POSITIVE LOGITS
    iology
    4.23
    iological
    3.22
    iologist
    2.64
    iop
    1.71
    iovascular
    1.56
    ionics
    1.48
    iol
    1.42
    ynthesis
    1.40
    iov
    1.37
    ioch
    1.27
    Activations Density 0.021%

    No Known Activations