© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 7279
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to music, such as genres, instruments, and musical characteristics, especially focusing on guitar-related elements

    oai_token-act-pair · gpt-3.5-turbo

    musical styles and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.75
     clot
    -0.69
     Genetic
    -0.68
     unres
    -0.68
     Geographic
    -0.66
     Centauri
    -0.66
     Nan
    -0.65
     Liang
    -0.65
     Spur
    -0.64
     Legisl
    -0.63
    POSITIVE LOGITS
    isphere
    1.07
     vocals
    1.00
     drummer
    0.99
     albums
    0.98
    itone
    0.97
    itars
    0.96
    ettes
    0.96
     tunes
    0.96
     lyrics
    0.94
     melodies
    0.94
    Activations Density 0.393%

    No Known Activations