© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4568
    Prev
    Next
    INDEX
    Explanations

    words related to sleeping and waking up

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to waking up or transitions from sleep

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    cer
    -0.79
    inates
    -0.75
    asse
    -0.70
     Forbidden
    -0.70
    cial
    -0.67
    inances
    -0.61
    cers
    -0.60
    asher
    -0.60
    adiq
    -0.60
    inished
    -0.59
    POSITIVE LOGITS
    fulness
    1.28
    mares
    1.02
    boarding
    0.95
    ful
    0.91
     up
    0.90
    mare
    0.87
    up
    0.86
    fully
    0.84
    ups
    0.80
     Up
    0.78
    Activations Density 0.035%

    No Known Activations