© 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. 1-RES-JB
    11. 14554
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of displaying something visually

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "displayed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctors
    -0.78
    allo
    -0.77
    trak
    -0.72
    unch
    -0.70
    lake
    -0.69
    ledge
    -0.68
    lez
    -0.68
    coal
    -0.68
    economic
    -0.66
    agan
    -0.65
    POSITIVE LOGITS
     displays
    1.40
     display
    1.16
     prominently
    1.09
     exhibits
    1.02
     displayed
    1.01
     displaying
    0.97
     Display
    0.95
     banners
    0.91
     Thumbnails
    0.88
    Display
    0.83
    Activations Density 0.009%

    No Known Activations