© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 20413
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "starting" or "beginning."

    oai_token-act-pair · gpt-3.5-turbo

    the word "start."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    iliary
    -0.86
    asca
    -0.76
    ugs
    -0.70
    ault
    -0.70
    otropic
    -0.69
    ortium
    -0.67
    cedented
    -0.67
    ournal
    -0.67
    itsch
    -0.67
    bey
    -0.66
    POSITIVE LOGITS
    starting
    1.00
    nings
    0.80
    OPLE
    0.75
    start
    0.73
    ablishment
    0.73
    started
    0.71
     anew
    0.71
     til
    0.70
    rek
    0.68
    Starting
    0.68
    Activations Density 0.043%

    No Known Activations