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

    Neuronpedia

    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. 8-RES-JB
    11. 17691
    Prev
    Next
    INDEX
    Explanations

    phrases related to music theory, chord progressions, and guitar riffs

    oai_token-act-pair · gpt-3.5-turbo

    references to musical chords and progressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indemn
    -0.89
     Gawker
    -0.88
     Govern
    -0.76
    quickShipAvailable
    -0.75
    Redd
    -0.72
     Walmart
    -0.72
     Costco
    -0.71
     Forbes
    -0.71
     Bris
    -0.70
    advertising
    -0.70
    POSITIVE LOGITS
     chords
    1.49
     guitar
    1.36
     sax
    1.33
     melody
    1.31
     piano
    1.30
     bass
    1.28
     melodies
    1.27
     guitars
    1.20
     vocals
    1.20
     percussion
    1.20
    Activations Density 0.322%

    No Known Activations