© 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. 6-RES-JB
    11. 20523
    Prev
    Next
    INDEX
    Explanations

    and activate on the word "professor"

    oai_token-act-pair · gpt-3.5-turbo

    references to academic professionals and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idiots
    -0.82
     Bulgar
    -0.74
     ultras
    -0.73
     chests
    -0.72
     Parties
    -0.70
     Italians
    -0.69
     Poles
    -0.68
     Cups
    -0.68
    hens
    -0.67
     Blacks
    -0.67
    POSITIVE LOGITS
     specializing
    0.87
    hunter
    0.83
     adjunct
    0.83
    etter
    0.71
    alyst
    0.71
    veland
    0.70
    href
    0.69
     emer
    0.69
    hattan
    0.69
    abase
    0.69
    Activations Density 0.119%

    No Known Activations