© 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. 1-RES-JB
    11. 22531
    Prev
    Next
    INDEX
    Explanations

    emails or email-related content

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term 'email' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Americ
    -0.75
     Chr
    -0.74
    OV
    -0.73
    UF
    -0.71
     PP
    -0.67
     Parks
    -0.64
     FI
    -0.63
     Coch
    -0.62
    neys
    -0.61
     NASCAR
    -0.61
    POSITIVE LOGITS
    mail
    1.56
    mails
    1.20
    Mail
    1.05
    email
    0.98
    boxes
    0.98
     inbox
    0.93
     mail
    0.92
    inator
    0.92
    ername
    0.88
    ertodd
    0.87
    Activations Density 0.011%

    No Known Activations