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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 9020
    Prev
    Next
    INDEX
    Explanations

    partial phrases related to performing or hearing music

    oai_token-act-pair · gpt-3.5-turbo

    elements related to music and lyrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afety
    -0.77
    Lens
    -0.76
    agate
    -0.75
     optic
    -0.74
    Reilly
    -0.73
     filament
    -0.73
     Investor
    -0.73
     Kov
    -0.73
     microsc
    -0.71
    Invest
    -0.71
    POSITIVE LOGITS
     lyrics
    2.34
     songs
    2.25
     sung
    2.18
     singers
    2.18
     song
    2.16
     singing
    2.10
     Songs
    1.97
     lyric
    1.97
     sings
    1.97
    yrics
    1.95
    Activations Density 0.564%

    No Known Activations