© 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. 9-RES-JB
    11. 24316
    Prev
    Next
    INDEX
    Explanations

    the word "twice" followed by a number in the same text snippet, indicating repetition or comparison

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "twice."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    andr
    -0.79
    UME
    -0.72
    endi
    -0.67
    ebted
    -0.66
    rals
    -0.65
    olve
    -0.65
    onite
    -0.64
     [&
    -0.63
    ament
    -0.63
    ogi
    -0.63
    POSITIVE LOGITS
     consecut
    0.87
    theless
    0.78
     apiece
    0.74
     dozen
    0.71
    entimes
    0.70
    fold
    0.67
    fif
    0.66
    orbit
    0.65
     dipping
    0.65
     thirds
    0.64
    Activations Density 0.021%

    No Known Activations