© 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. 10-RES-JB
    11. 3499
    Prev
    Next
    INDEX
    Explanations

    numerical values related to costs, prices, and budgets

    oai_token-act-pair · gpt-3.5-turbo

    commas and their frequency in statistical or financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ²¾
    -0.77
    ARCH
    -0.73
    sburg
    -0.71
    ESE
    -0.65
    NetMessage
    -0.63
    algia
    -0.62
    irie
    -0.61
    oslav
    -0.60
     forums
    -0.58
    Preview
    -0.58
    POSITIVE LOGITS
    depending
    1.17
     depending
    1.09
     compared
    1.06
     according
    1.02
     whereas
    0.99
    000
    0.99
     equivalent
    0.98
     whichever
    0.97
     roughly
    0.91
     assuming
    0.91
    Activations Density 0.167%

    No Known Activations