© 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. 8-RES-JB
    11. 6290
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals named "Justin"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals named Justin, particularly in the context of notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mileage
    -0.75
     extremes
    -0.74
    wark
    -0.72
    topic
    -0.68
    ansas
    -0.67
    worldly
    -0.63
    cheat
    -0.62
    unda
    -0.61
     UA
    -0.61
    rums
    -0.61
    POSITIVE LOGITS
     Bieber
    1.43
     Trudeau
    1.14
     Timber
    1.13
     Vernon
    0.88
    ian
    0.87
    eland
    0.83
     Finch
    0.81
    ians
    0.81
    Justin
    0.81
    ique
    0.79
    Activations Density 0.025%

    No Known Activations