© 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. 1-RES-JB
    11. 20330
    Prev
    Next
    INDEX
    Explanations

    references to individuals in positions of authority or leadership, particularly those with the title "Chief"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals holding chief positions or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etimes
    -0.77
    avery
    -0.73
    nikov
    -0.72
    schild
    -0.72
    aver
    -0.72
    debian
    -0.70
    adr
    -0.70
    ICAN
    -0.69
    berra
    -0.69
    vous
    -0.68
    POSITIVE LOGITS
     Chief
    1.23
    Chief
    1.13
     chief
    0.85
    chief
    0.83
     Engineer
    0.80
     Marshal
    0.80
     Executive
    0.80
     Editor
    0.79
     Officer
    0.78
     Analyst
    0.78
    Activations Density 0.009%

    No Known Activations