© 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. 22003
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Rebecca"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Rebecca."

    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
    teenth
    -0.90
    pora
    -0.76
    awaru
    -0.74
     controllers
    -0.70
    ician
    -0.70
    llular
    -0.69
    matic
    -0.69
     dracon
    -0.68
    actic
    -0.68
    ctica
    -0.67
    POSITIVE LOGITS
     McKenzie
    0.94
    issance
    0.89
     Rebecca
    0.85
     Lopez
    0.84
     Koen
    0.82
     Lynn
    0.77
    becca
    0.76
    anne
    0.76
    leigh
    0.76
     Hernandez
    0.74
    Activations Density 0.006%

    No Known Activations