© 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. 11-RES-JB
    11. 14968
    Prev
    Next
    INDEX
    Explanations

    phrases related to sleep deprivation and its effects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sleep and fatigue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.81
    Jar
    -0.81
    Forge
    -0.79
     certs
    -0.79
    VG
    -0.74
    guns
    -0.74
     Cutter
    -0.74
    manship
    -0.73
     RG
    -0.73
     Gou
    -0.72
    POSITIVE LOGITS
     sleep
    2.24
    Sleep
    2.17
     Sleep
    2.10
     sleeping
    2.04
    sleep
    2.02
     sleeps
    1.94
     slept
    1.92
     asleep
    1.84
     Sleeping
    1.84
     insomnia
    1.80
    Activations Density 0.376%

    No Known Activations