© 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
    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. 24175
    Prev
    Next
    INDEX
    Explanations

    characters and terms related to typography and font design

    oai_token-act-pair · gpt-3.5-turbo

    references to fonts and typography

    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
    apeake
    -0.84
    jury
    -0.83
    ickets
    -0.80
    lethal
    -0.77
     detonated
    -0.76
    rake
    -0.73
     Dale
    -0.72
     methamphetamine
    -0.72
     fracking
    -0.70
    ****
    -0.70
    POSITIVE LOGITS
     fonts
    2.22
     font
    2.17
    Font
    1.99
     Font
    1.89
    font
    1.86
     glyph
    1.79
     Unicode
    1.62
     typ
    1.45
     ital
    1.41
    FontSize
    1.39
    Activations Density 0.248%

    No Known Activations