© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11426
    Prev
    Next
    INDEX
    Explanations

    references to emails or mail within text

    oai_token-act-pair · gpt-3.5-turbo

    references to email and mail-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ETF
    -0.74
    oulos
    -0.73
    razil
    -0.70
    essential
    -0.67
    issan
    -0.64
    ietal
    -0.63
     Haram
    -0.63
    DES
    -0.63
    66666666
    -0.62
     LORD
    -0.62
    POSITIVE LOGITS
    boxes
    1.35
    bag
    1.22
    box
    1.05
    bags
    1.05
    mail
    0.98
     inbox
    0.88
     mail
    0.87
    enstein
    0.85
    letter
    0.83
    email
    0.81
    Activations Density 0.024%

    No Known Activations