© 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. 2-RES-JB
    11. 21959
    Prev
    Next
    INDEX
    Explanations

    references to the numeric term "six"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the number six

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lance
    -0.76
    itivity
    -0.73
    iah
    -0.66
    ÃĥÃĤ
    -0.66
    achu
    -0.62
     Collider
    -0.62
    rade
    -0.62
     Congratulations
    -0.61
     guiIcon
    -0.61
    plom
    -0.60
    POSITIVE LOGITS
    teenth
    1.86
    teen
    1.77
     months
    1.28
    een
    1.13
     weeks
    1.11
     hundred
    1.03
     days
    0.96
     Months
    0.93
    eenth
    0.93
     hours
    0.91
    Activations Density 0.029%

    No Known Activations