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. 6-RES-JB
    6. 20975
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events and amendments in the United States Constitution

    oai_token-act-pair · gpt-3.5-turbo

    references to important amendments and historical events related to American rights and government

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.90
    alone
    -0.71
    akuya
    -0.68
    POR
    -0.68
    utics
    -0.68
    lessly
    -0.67
    govtrack
    -0.67
    boards
    -0.64
    BIL
    -0.64
    bourg
    -0.62
    POSITIVE LOGITS
     Era
    1.15
     Revolution
    1.06
     Declaration
    0.99
     Presidency
    0.96
     era
    0.90
     Empire
    0.88
     Continent
    0.88
     Commission
    0.87
     Amendment
    0.87
     Convention
    0.85
    Activations Density 0.237%

    No Known Activations