© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20599
    Prev
    Next
    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of email addresses and associated details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "},"
    -0.72
    oppable
    -0.71
     Survive
    -0.66
     Underground
    -0.61
     tutorials
    -0.59
    "},{"
    -0.58
     lashes
    -0.55
     Tsukuyomi
    -0.55
     Archae
    -0.55
     rhy
    -0.54
    POSITIVE LOGITS
    Subject
    1.09
     Subject
    1.09
    Sent
    0.98
     Sent
    0.92
     Huma
    0.91
    Date
    0.88
    mail
    0.85
    ullivan
    0.83
     forwarded
    0.83
     Abedin
    0.79
    Activations Density 0.109%

    No Known Activations