© 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. 7463
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a person named "Campbell"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Campbell."

    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
    lihood
    -0.82
    olitics
    -0.79
    liest
    -0.75
    initialized
    -0.75
    LEASE
    -0.71
    fix
    -0.67
    eways
    -0.67
    rored
    -0.66
    ctx
    -0.65
    ntil
    -0.65
    POSITIVE LOGITS
     Campbell
    1.01
     Soup
    0.98
    otte
    0.92
    iac
    0.87
    gren
    0.85
    shire
    0.83
    icum
    0.79
    ite
    0.79
     Newman
    0.78
    ibur
    0.77
    Activations Density 0.009%

    No Known Activations