© 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. 3-RES-JB
    11. 17788
    Prev
    Next
    INDEX
    Explanations

    the presence of repeated instances of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the name "Monet" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionGroup
    -0.88
    hips
    -0.73
    æĸ¹
    -0.72
    lished
    -0.69
    lishes
    -0.67
    aturdays
    -0.67
    orsi
    -0.66
    achusetts
    -0.63
    ãĤ¸
    -0.63
    ruary
    -0.62
    POSITIVE LOGITS
    gger
    0.93
     Hundred
    0.89
    xit
    0.87
    xus
    0.84
    getic
    0.83
    cott
    0.82
    boarding
    0.81
    hoe
    0.79
    horn
    0.78
    cone
    0.75
    Activations Density 0.024%

    No Known Activations