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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3228
    Prev
    Next
    INDEX
    Explanations

    mentions of "private servers" in the context of emails

    oai_token-act-pair · gpt-3.5-turbo

    terms related to Hillary Clinton's use of private email servers

    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
    umar
    -0.88
    crow
    -0.78
    UP
    -0.74
     Torn
    -0.73
    odder
    -0.72
    KR
    -0.71
    erenn
    -0.71
    à¨
    -0.70
    RAG
    -0.69
    NT
    -0.69
    POSITIVE LOGITS
     Clinton
    0.87
     trove
    0.87
    ghazi
    0.83
     scandal
    0.80
     conspiracy
    0.79
     aides
    0.79
    ovo
    0.78
     Benghazi
    0.78
     scandals
    0.78
     unlawfully
    0.78
    Activations Density 0.074%

    No Known Activations