© 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. 0-RES-JB
    11. 4029
    Prev
    Next
    INDEX
    Explanations

    mentions of music-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to music, including its impact, genres, and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bowen
    -0.83
     Siber
    -0.67
    aunder
    -0.67
    regn
    -0.67
     Granger
    -0.67
    Deploy
    -0.66
    rored
    -0.66
     miscar
    -0.65
    ivot
    -0.65
     Cheney
    -0.64
    POSITIVE LOGITS
     music
    3.43
    music
    2.72
     Music
    2.59
    Music
    2.53
     musical
    2.09
     songs
    2.00
     musicians
    1.98
     tunes
    1.94
     soundtrack
    1.93
     song
    1.87
    Activations Density 0.020%

    No Known Activations