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. 3-RES-JB
    6. 1342
    Prev
    Next
    INDEX
    Explanations

    references to Presidents, especially President Donald Trump and President Barack Obama

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "President."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawdownloadcloneembedreportprint
    -0.91
    MpServer
    -0.78
    Ĥª
    -0.76
    lot
    -0.74
    sbm
    -0.71
    eros
    -0.71
    âĵĺ
    -0.71
    ļéĨĴ
    -0.70
    PsyNetMessage
    -0.69
    obyl
    -0.69
    POSITIVE LOGITS
     Barack
    1.09
     Lyndon
    1.02
     Obama
    0.92
     Donald
    0.92
     President
    0.90
     Accountability
    0.88
    ially
    0.87
     Truman
    0.86
     Recep
    0.85
     Dwight
    0.85
    Activations Density 0.041%

    No Known Activations