© 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. 9-RES-JB
    11. 9845
    Prev
    Next
    INDEX
    Explanations

    email subject lines that contain a mix of generic phrases and email-related terms

    oai_token-act-pair · gpt-3.5-turbo

    the structure and formatting of email components and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     premie
    -0.72
     Wander
    -0.72
     dives
    -0.71
     signage
    -0.70
     Survive
    -0.70
     Unle
    -0.67
     Expand
    -0.65
     Laugh
    -0.64
     IMAGES
    -0.63
    "},"
    -0.62
    POSITIVE LOGITS
    olicited
    0.95
    ullivan
    0.94
     Abedin
    0.93
    mail
    0.91
    reply
    0.90
    >>>>
    0.88
    Date
    0.88
    Subject
    0.87
     forwarded
    0.86
    date
    0.86
    Activations Density 0.152%

    No Known Activations