© 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. 10-RES-JB
    11. 10058
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to physics and mathematics, like particles, functions, and forces

    oai_token-act-pair · gpt-3.5-turbo

    specific letters or symbols related to scientific and mathematical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advertising
    -0.66
    Redd
    -0.59
     fulfillment
    -0.58
    Gaza
    -0.57
    Chel
    -0.57
    Environment
    -0.55
    NetMessage
    -0.55
    Alabama
    -0.54
    Safety
    -0.52
    PK
    -0.52
    POSITIVE LOGITS
    xual
    1.16
    EStream
    0.73
    xon
    0.71
    uthor
    0.71
    ulhu
    0.71
    roma
    0.69
    ccording
    0.69
     tha
    0.68
    ription
    0.67
    erent
    0.66
    Activations Density 0.194%

    No Known Activations