© 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 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. 13330
    Prev
    Next
    INDEX
    Explanations

    text related to copying and sharing content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Copy."

    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
     camp
    -0.75
    å
    -0.74
     mil
    -0.69
     struggle
    -0.67
     mood
    -0.67
     settlements
    -0.66
     prow
    -0.66
     buoy
    -0.65
     sympath
    -0.64
     irrit
    -0.64
    POSITIVE LOGITS
     Copy
    3.91
    Copy
    2.41
    copy
    1.85
     copy
    1.45
     Paste
    1.36
     Clone
    1.33
     copies
    1.29
     Dupl
    1.22
     copied
    1.21
     copying
    1.17
    Activations Density 0.028%

    No Known Activations