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. 10-RES-JB
    6. 15479
    Prev
    Next
    INDEX
    Explanations

    words related to music, especially musical genres and elements

    oai_token-act-pair · gpt-3.5-turbo

    references to music and musicals

    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
    bare
    -0.77
    lessly
    -0.73
    agher
    -0.72
    hov
    -0.69
    chenko
    -0.66
    lessness
    -0.65
    20439
    -0.65
     Admin
    -0.65
    llan
    -0.65
    xon
    -0.64
    POSITIVE LOGITS
     accompan
    1.13
     genres
    1.10
    ity
    1.06
     theater
    1.05
     theatre
    1.04
     notation
    0.95
     instrument
    0.95
     Instrument
    0.92
     genre
    0.92
     musical
    0.92
    Activations Density 0.022%

    No Known Activations