© 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 EvalsExportsinterp-engineNEWAPI 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. 20925
    Prev
    Next
    INDEX
    Explanations

    repeated symbols or characters

    oai_token-act-pair · gpt-3.5-turbo

    symbols and special characters used for emphasis or formatting in text

    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
    xus
    -0.90
    iple
    -0.82
    unal
    -0.79
    est
    -0.78
    tek
    -0.75
    oola
    -0.74
    sters
    -0.73
    zzle
    -0.72
    ackle
    -0.71
    ster
    -0.71
    POSITIVE LOGITS
    _>
    1.42
     Contents
    0.89
     Preferences
    0.82
    =~=~
    0.82
    ĸļ
    0.77
    =>
    0.77
     ********************************
    0.70
     Taken
    0.70
    >>>>
    0.70
    Present
    0.67
    Activations Density 0.035%

    No Known Activations