© 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. 0-RES-JB
    11. 1769
    Prev
    Next
    INDEX
    Explanations

    highlights or notable points in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "highlights."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ther
    -0.75
    ystem
    -0.72
     disposed
    -0.71
    ifice
    -0.63
    itary
    -0.62
    ilon
    -0.61
    perate
    -0.60
    uu
    -0.60
     controlled
    -0.59
    ct
    -0.59
    POSITIVE LOGITS
     highlights
    3.80
     highlight
    2.46
     Highlights
    2.28
     highlighting
    1.66
     highlighted
    1.57
     showcases
    1.55
     underscores
    1.47
     outlines
    1.39
     contrasts
    1.38
     illustrates
    1.25
    Activations Density 0.009%

    No Known Activations