Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15004
    Prev
    Next
    INDEX
    Explanations

    references to emails and servers related to Hillary Clinton's email controversy

    oai_token-act-pair · gpt-3.5-turbo

    references to Hillary Clinton's email server and related terms regarding private communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umar
    -0.82
    ksh
    -0.79
     Wim
    -0.75
    STAR
    -0.75
    axis
    -0.73
    KR
    -0.72
     Dudley
    -0.72
    NT
    -0.70
    UP
    -0.70
    erenn
    -0.69
    POSITIVE LOGITS
     Clinton
    0.92
     trove
    0.88
    ghazi
    0.87
    umenthal
    0.87
     aides
    0.84
     scandals
    0.83
    Clinton
    0.82
     Hillary
    0.80
     aide
    0.80
     dumps
    0.80
    Activations Density 0.059%

    No Known Activations