© 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. 3-RES-JB
    11. 1799
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, particularly the name "Rebecca"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Rebecca."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teenth
    -0.85
    actic
    -0.74
    awaru
    -0.73
    pora
    -0.71
    */(
    -0.69
    ician
    -0.68
    ategic
    -0.67
    llular
    -0.67
    ibaba
    -0.67
     dracon
    -0.67
    POSITIVE LOGITS
     Lopez
    0.89
     McKenzie
    0.89
     Rebecca
    0.88
    issance
    0.86
    ãĤ©
    0.82
    anne
    0.79
     Hernandez
    0.78
     Koen
    0.76
    becca
    0.76
     Clement
    0.74
    Activations Density 0.011%

    No Known Activations