© 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. 19250
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "awakening"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Wake," particularly in contexts suggesting a call to action or awareness

    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
     stones
    -0.78
    stones
    -0.70
     poles
    -0.70
     sellers
    -0.65
    metadata
    -0.65
     phil
    -0.65
     brass
    -0.64
     intermedi
    -0.62
     stamped
    -0.62
     photographers
    -0.62
    POSITIVE LOGITS
     Wake
    4.26
    wake
    1.89
     wake
    1.60
     Raleigh
    1.17
     wakes
    1.17
     Chapel
    1.00
     Sleep
    0.97
     waking
    0.97
     Clemson
    0.96
     Winston
    0.95
    Activations Density 0.018%

    No Known Activations