Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8543
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of instruments, such as musical instruments, scientific instruments, and tools

    oai_token-act-pair · gpt-3.5-turbo

    references to musical or scientific instruments

    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
    advertising
    -0.66
     Kendall
    -0.63
    ached
    -0.63
    ookie
    -0.62
     Rath
    -0.62
     bumped
    -0.62
    edia
    -0.61
     Ble
    -0.61
    YY
    -0.61
    erate
    -0.60
    POSITIVE LOGITS
     instruments
    4.11
     instrument
    3.10
     Instruments
    2.75
     Instrument
    2.27
    strument
    1.94
     guitars
    1.65
     tools
    1.44
     drums
    1.38
     organs
    1.31
     percussion
    1.28
    Activations Density 0.023%

    No Known Activations