© 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. 19247
    Prev
    Next
    INDEX
    Explanations

    verbatims or copies of text in a long document

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "copied" and variations of the word "copying"

    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
     sust
    -0.68
    ady
    -0.64
     Barker
    -0.62
    âĢİ
    -0.62
     relief
    -0.61
     stability
    -0.61
    stad
    -0.60
    intensity
    -0.60
    udder
    -0.60
    ür
    -0.59
    POSITIVE LOGITS
     copied
    3.73
     copying
    3.05
     copy
    2.00
    copy
    1.92
     plagiar
    1.89
     Copy
    1.84
     copies
    1.77
    Copy
    1.69
     duplication
    1.32
     dupl
    1.29
    Activations Density 0.021%

    No Known Activations