© 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. 4-RES-JB
    11. 722
    Prev
    Next
    INDEX
    Explanations

    email-related messages that mention an invalid email address

    oai_token-act-pair · gpt-3.5-turbo

    references to invalid email addresses

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

    No Comments

    Negative Logits
    ItemTracker
    -0.93
    itive
    -0.87
    icles
    -0.86
    icle
    -0.85
    apesh
    -0.72
    igs
    -0.72
    profit
    -0.71
    shr
    -0.70
    hma
    -0.69
    atively
    -0.68
    POSITIVE LOGITS
     Email
    0.98
     Thumbnails
    0.96
     Emails
    0.90
     sender
    0.86
     inbox
    0.84
     Address
    0.80
    Email
    0.74
     Wire
    0.74
     login
    0.74
    Send
    0.73
    Activations Density 0.009%

    No Known Activations