© 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. 20793
    Prev
    Next
    INDEX
    Explanations

    double 'C' characters as a distinguishing pattern

    oai_token-act-pair · gpt-3.5-turbo

    sequences or patterns in data that suggest importance or significance

    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
     eleph
    -0.97
     casc
    -0.93
     soak
    -0.90
     downright
    -0.88
     crunch
    -0.86
     oun
    -0.84
     darn
    -0.83
     damned
    -0.82
     packed
    -0.82
     screwed
    -0.82
    POSITIVE LOGITS
    Appearances
    2.09
    Trivia
    2.04
    References
    2.03
    Appearance
    1.93
    Contents
    1.93
    History
    1.90
    Notable
    1.89
    Gallery
    1.88
    Development
    1.80
    External
    1.77
    Activations Density 0.195%

    No Known Activations