© 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. 10-RES-JB
    11. 8555
    Prev
    Next
    INDEX
    Explanations

    email-related terms and prompts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to email addresses and user input for email subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eren
    -0.73
    ewitness
    -0.69
     heck
    -0.69
    hung
    -0.68
    arios
    -0.64
    ãĥ´
    -0.64
    oqu
    -0.64
    uers
    -0.64
    dust
    -0.61
    ãĤ©
    -0.59
    POSITIVE LOGITS
     Email
    0.74
     Inquiry
    0.74
     {*
    0.71
     Password
    0.71
     password
    0.67
     PayPal
    0.67
     Username
    0.67
     login
    0.65
     address
    0.64
     Login
    0.63
    Activations Density 0.012%

    No Known Activations