© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14873
    Prev
    Next
    INDEX
    Explanations

    emails mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to email communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gears
    -0.81
     heights
    -0.74
     squats
    -0.73
     braces
    -0.70
     hotter
    -0.69
     Ernst
    -0.69
     clocks
    -0.68
     oils
    -0.66
     hinges
    -0.65
     realism
    -0.65
    POSITIVE LOGITS
    Mail
    1.37
    mail
    1.34
    mails
    1.05
    letter
    1.05
     mail
    1.01
    MA
    0.94
    tymology
    0.93
    Email
    0.92
    email
    0.90
    Newsletter
    0.90
    Activations Density 0.030%

    No Known Activations