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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 3230
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "constitutional."

    oai_token-act-pair · gpt-3.5-turbo

    references to constitutional law and amendments

    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
    feed
    -0.73
     teased
    -0.72
     Spread
    -0.71
     Feed
    -0.68
     spreads
    -0.67
    Maker
    -0.67
    ushed
    -0.67
    wards
    -0.65
     spread
    -0.64
     Dri
    -0.63
    POSITIVE LOGITS
     constitutional
    3.54
     Constitutional
    2.99
    constitutional
    2.56
     constitutionally
    2.30
     unconstitutional
    1.99
     constitution
    1.81
     Constitution
    1.79
     statutory
    1.48
     legal
    1.45
     judicial
    1.41
    Activations Density 0.016%

    No Known Activations