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. 11-RES-JB
    6. 10695
    Prev
    Next
    INDEX
    Explanations

    references and discussions related to constitutional amendments, particularly the First and Fourth Amendments

    oai_token-act-pair · gpt-3.5-turbo

    references to the First and Fourth Amendments of the U.S. Constitution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akuya
    -0.67
     blitz
    -0.64
    kj
    -0.64
     cous
    -0.64
    stead
    -0.62
    phis
    -0.62
    acters
    -0.62
     begg
    -0.62
    steamapps
    -0.61
     scr
    -0.61
    POSITIVE LOGITS
     Amendment
    1.82
     Amendments
    1.49
     amendment
    1.36
     Amend
    1.28
     Clause
    1.13
     Circuit
    1.04
     amendments
    1.00
    endment
    0.94
     Article
    0.89
     Term
    0.88
    Activations Density 0.033%

    No Known Activations