© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 20422
    Prev
    Next
    INDEX
    Explanations

    references to music or musicians

    oai_token-act-pair · gpt-3.5-turbo

    terms related to music

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Bye
    -0.80
     WD
    -0.72
     Wyoming
    -0.69
     1910
    -0.68
    REAM
    -0.67
     Dull
    -0.67
     Highlands
    -0.67
     1860
    -0.63
     EDITION
    -0.61
     slee
    -0.61
    POSITIVE LOGITS
    mus
    1.50
    olean
    0.97
    cles
    0.97
    achus
    0.96
    andise
    0.94
    encer
    0.93
    uria
    0.92
    atsu
    0.92
    cled
    0.92
    cle
    0.91
    Activations Density 0.004%

    No Known Activations