Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 9937
    Prev
    Next
    INDEX
    Explanations

    instances of the word "voluntary"

    oai_token-act-pair · gpt-3.5-turbo

    references to voluntary actions or agreements

    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
     Expand
    -0.79
     Indies
    -0.74
    lords
    -0.74
    marks
    -0.73
    rums
    -0.72
    mill
    -0.70
    geist
    -0.70
     Tycoon
    -0.70
    ean
    -0.69
     Blessed
    -0.68
    POSITIVE LOGITS
    untary
    1.40
     voluntary
    1.30
    untarily
    1.16
     manslaughter
    1.14
     involuntary
    1.12
     voluntarily
    0.91
    unte
    0.91
     cessation
    0.87
     reluct
    0.82
     compensation
    0.82
    Activations Density 0.009%

    No Known Activations