© 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. 9-RES-JB
    11. 23670
    Prev
    Next
    INDEX
    Explanations

    commas and dialogue tags

    oai_token-act-pair · gpt-3.5-turbo

    commas used in dialogue or speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.80
    olves
    -0.71
    iciary
    -0.66
    izon
    -0.62
    imore
    -0.61
    orts
    -0.61
    aban
    -0.58
     happ
    -0.57
    abase
    -0.57
    hess
    -0.57
    POSITIVE LOGITS
     "'
    1.13
     "âĢ¦
    1.10
     '[
    1.00
     "(
    0.98
     "$
    0.97
     "...
    0.94
     hey
    0.93
     "[
    0.92
     `
    0.91
     ""
    0.90
    Activations Density 0.099%

    No Known Activations