© 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. 4-RES-JB
    11. 10498
    Prev
    Next
    INDEX
    Explanations

    names or words with the sequence "edd"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to individuals, particularly in the context of names or notable titles

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

    No Comments

    Negative Logits
    Ko
    -0.70
     Stras
    -0.69
    WB
    -0.66
    FUL
    -0.65
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.63
     Pav
    -0.63
     Appalachian
    -0.63
    Ô
    -0.62
     Freedom
    -0.61
    QUI
    -0.61
    POSITIVE LOGITS
    ication
    1.02
    edd
    1.01
    ensen
    0.98
    icated
    0.96
    ding
    0.91
    uce
    0.89
    ington
    0.88
    irect
    0.87
    ried
    0.87
    uct
    0.86
    Activations Density 0.013%

    No Known Activations