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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3898
    Prev
    Next
    INDEX
    Explanations

    phrases related to musical elements, specifically guitar "riffs."

    oai_token-act-pair · gpt-3.5-turbo

    references to musical elements, specifically guitar riffs

    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
    idad
    -0.65
    asia
    -0.64
     Laur
    -0.63
    coming
    -0.62
    lymp
    -0.60
    iolet
    -0.60
    omore
    -0.59
    certain
    -0.59
    ggle
    -0.59
    uchs
    -0.59
    POSITIVE LOGITS
     riff
    1.19
    enegger
    0.85
    ="#
    0.80
    ety
    0.75
    heit
    0.73
    artisan
    0.73
    orno
    0.71
     guiActiveUn
    0.71
    iffs
    0.70
     tune
    0.70
    Activations Density 0.009%

    No Known Activations