© 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. 1886
    Prev
    Next
    INDEX
    Explanations

    names or references to individuals named "Matt"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Matt."

    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
    estic
    -0.68
    ²
    -0.67
    agara
    -0.66
    kaya
    -0.65
    iru
    -0.65
    arbon
    -0.64
     Â
    -0.64
     largeDownload
    -0.63
     bureaucr
    -0.62
     cro
    -0.62
    POSITIVE LOGITS
     Matt
    3.24
    Matt
    2.87
     Matthew
    1.92
     matt
    1.87
    Matthew
    1.59
     Mitch
    1.53
     Kyle
    1.43
     Dustin
    1.41
     Josh
    1.41
     Zach
    1.41
    Activations Density 0.021%

    No Known Activations