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. 10-RES-JB
    6. 1500
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical figures, specifically Franklin Delano Roosevelt

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Franklin D. Roosevelt and related historical figures or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ded
    -0.95
    rons
    -0.94
    uling
    -0.91
    rar
    -0.91
    ombat
    -0.88
    lass
    -0.84
    untu
    -0.83
    ener
    -0.83
    akening
    -0.83
    rum
    -0.82
    POSITIVE LOGITS
     Roosevelt
    1.21
     Square
    0.99
     County
    0.94
     Parkway
    0.91
     Parish
    0.89
     Armory
    0.87
     Pierce
    0.86
     Institution
    0.85
     Avenue
    0.84
     Jefferson
    0.83
    Activations Density 0.096%

    No Known Activations