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. 3935
    Prev
    Next
    INDEX
    Explanations

    names of political leaders such as "presidents."

    oai_token-act-pair · gpt-3.5-turbo

    the term "presidents" and related references to various presidents

    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
    kit
    -0.79
     kit
    -0.65
    starter
    -0.63
    idi
    -0.63
    ernaut
    -0.62
    UK
    -0.58
    cel
    -0.58
    zyk
    -0.58
    dk
    -0.58
     newcomer
    -0.58
    POSITIVE LOGITS
     presidents
    3.83
     Presidents
    3.28
     administrations
    2.14
     governors
    1.97
     secretaries
    1.88
     mayors
    1.88
     CEOs
    1.68
     Governors
    1.54
    President
    1.41
     senators
    1.37
    Activations Density 0.012%

    No Known Activations