© 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. 1-RES-JB
    11. 14433
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Viola"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Viola" and its associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    dash
    -0.84
    erald
    -0.71
    mares
    -0.71
    peak
    -0.69
    ointment
    -0.69
    dress
    -0.68
     Herald
    -0.66
    pread
    -0.62
    è¦ļéĨĴ
    -0.61
    canon
    -0.60
    POSITIVE LOGITS
    viol
    1.48
     Viol
    1.33
     viol
    1.32
     violin
    1.16
    Viol
    1.05
     pian
    0.93
     Orchestra
    0.87
    amental
    0.79
     Instrument
    0.79
    alties
    0.76
    Activations Density 0.009%

    No Known Activations