© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 5218
    Prev
    Next
    INDEX
    Explanations

    names or words related to the name "Marc" or variations like "Marco" or "Marquez"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "mar" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    culosis
    -0.76
    BOOK
    -0.74
    enhagen
    -0.68
    uyomi
    -0.68
    umerable
    -0.68
    æ©Ł
    -0.67
    arantine
    -0.66
    efficients
    -0.65
    elsius
    -0.64
    OLOGY
    -0.63
    POSITIVE LOGITS
     mar
    1.03
    quet
    0.90
    quez
    0.85
    ried
    0.82
    quer
    0.82
    ÃŃa
    0.78
    inated
    0.75
     Rafael
    0.75
    aquin
    0.74
    accompan
    0.73
    Activations Density 0.004%

    No Known Activations