© 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. 13557
    Prev
    Next
    INDEX
    Explanations

    words related to quietness or calmness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "quiet"

    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
    Adult
    -0.68
     Ferr
    -0.67
    DNA
    -0.67
    amide
    -0.65
    sticks
    -0.64
    UGC
    -0.63
    allion
    -0.62
     Applic
    -0.62
    /(
    -0.62
     Adult
    -0.61
    POSITIVE LOGITS
     quiet
    3.64
     quieter
    2.67
     silent
    2.33
    quiet
    2.09
     Quiet
    2.09
     silence
    1.95
     calm
    1.95
     noisy
    1.56
     quietly
    1.54
     tranqu
    1.45
    Activations Density 0.013%

    No Known Activations