© 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. 4-RES-JB
    11. 602
    Prev
    Next
    INDEX
    Explanations

    mentions of musicians

    oai_token-act-pair · gpt-3.5-turbo

    references to musicians and their roles in music production

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

    No Comments

    Negative Logits
    elsius
    -0.73
     vacant
    -0.71
     Pradesh
    -0.67
    zers
    -0.66
    wered
    -0.63
     Forestry
    -0.63
    adra
    -0.62
     Paragu
    -0.60
     Matter
    -0.60
    plings
    -0.60
    POSITIVE LOGITS
     sax
    0.93
     musicians
    0.91
     laureate
    0.89
     royalties
    0.84
     pian
    0.83
     musician
    0.80
    atically
    0.79
    esses
    0.77
     composer
    0.77
    Artist
    0.77
    Activations Density 0.025%

    No Known Activations