© 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. 7-RES-JB
    11. 20552
    Prev
    Next
    INDEX
    Explanations

    the number "two" or "three" that appears in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of quantities, particularly the numbers two and three

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obin
    -0.78
    vention
    -0.76
    urgy
    -0.72
    biology
    -0.71
     [&
    -0.71
    Temperature
    -0.69
    urden
    -0.69
    agame
    -0.67
    heter
    -0.67
    ãĤ´ãĥ³
    -0.64
    POSITIVE LOGITS
    teen
    1.06
    teenth
    1.05
     dozen
    0.98
     successive
    0.93
     consecutive
    0.93
     hundred
    0.91
     unidentified
    0.87
     unnamed
    0.86
     months
    0.86
     weeks
    0.83
    Activations Density 0.173%

    No Known Activations