© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 17181
    Prev
    Next
    INDEX
    Explanations

    mentions of people named Justin, most likely focusing on the name itself rather than any specific context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Justin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wark
    -0.79
     extremes
    -0.70
     mileage
    -0.68
    worldly
    -0.68
    metic
    -0.65
    circ
    -0.65
    ansas
    -0.63
     circ
    -0.61
     womb
    -0.61
    recy
    -0.60
    POSITIVE LOGITS
     Bieber
    1.35
     Timber
    1.17
     Trudeau
    1.07
     Vernon
    0.87
    ian
    0.81
    onymous
    0.81
     Bour
    0.79
     Upton
    0.75
     Kut
    0.74
     Abdel
    0.73
    Activations Density 0.037%

    No Known Activations