Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21065
    Prev
    Next
    INDEX
    Explanations

    references to sleep or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to sleep and its importance

    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
    Jar
    -0.78
    quist
    -0.75
    hur
    -0.74
    notation
    -0.72
    ophone
    -0.72
     Rossi
    -0.70
    Commercial
    -0.69
     Magnum
    -0.69
     Newman
    -0.68
    ocrat
    -0.68
    POSITIVE LOGITS
     sleep
    3.81
    sleep
    2.74
    Sleep
    2.68
     Sleep
    2.63
     sleeps
    2.28
     sleeping
    2.20
     slept
    2.14
     asleep
    1.85
    leep
    1.77
     insomnia
    1.64
    Activations Density 0.009%

    No Known Activations