© 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. 10063
    Prev
    Next
    INDEX
    Explanations

    instances of falling asleep or related scenarios

    oai_token-act-pair · gpt-3.5-turbo

    instances of falling asleep

    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
    Ĵ
    -0.67
     Cross
    -0.65
     Ric
    -0.64
    ival
    -0.63
     Reprodu
    -0.62
     Ge
    -0.62
    erve
    -0.61
    credit
    -0.61
     Equity
    -0.60
     Conflict
    -0.59
    POSITIVE LOGITS
     asleep
    3.99
     awake
    2.00
    leep
    1.68
     slept
    1.65
     sleeps
    1.62
     sleeping
    1.61
     awoken
    1.50
     sleep
    1.46
     unconscious
    1.37
     sleepy
    1.31
    Activations Density 0.010%

    No Known Activations