© 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. 0-RES-JB
    11. 5373
    Prev
    Next
    INDEX
    Explanations

    references to musicians

    oai_token-act-pair · gpt-3.5-turbo

    references to musicians and their roles in the music industry

    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
    Ev
    -0.73
    ea
    -0.69
     dumped
    -0.67
     dump
    -0.66
     Kell
    -0.65
     agg
    -0.65
     Cache
    -0.63
     containment
    -0.63
     Atk
    -0.62
     Ev
    -0.61
    POSITIVE LOGITS
     musicians
    3.29
     musician
    2.67
     orchestra
    2.21
     singers
    2.15
     drummer
    2.14
     pian
    2.04
     guitarist
    2.01
     musical
    1.99
     composer
    1.99
     Orchestra
    1.97
    Activations Density 0.034%

    No Known Activations