© 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. 0-RES-JB
    11. 8175
    Prev
    Next
    INDEX
    Explanations

    numerical digits, particularly with a focus on numbers in the nine-digit range

    oai_token-act-pair · gpt-3.5-turbo

    digits and references to numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     politics
    -0.67
    uno
    -0.67
    angu
    -0.66
     Haz
    -0.65
    ixtures
    -0.62
     Cabin
    -0.62
    rites
    -0.61
     Atmosp
    -0.60
     Ant
    -0.60
     stirred
    -0.59
    POSITIVE LOGITS
     digit
    3.82
    digit
    3.50
     digits
    3.03
    Dig
    1.69
    dig
    1.55
     Dig
    1.39
    digital
    1.16
     decimal
    1.13
     digitally
    1.03
    figure
    0.97
    Activations Density 0.014%

    No Known Activations