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

    Neuronpedia

    Jacobian LensNEW
    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. 3861
    Prev
    Next
    INDEX
    Explanations

    mentions of military ranks and titles, particularly those related to leadership roles

    oai_token-act-pair · gpt-3.5-turbo

    references to military ranks or titles

    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
    icles
    -0.75
    ipedia
    -0.66
    icle
    -0.65
    roma
    -0.65
    employment
    -0.65
    rin
    -0.63
    arling
    -0.62
    Democrats
    -0.62
    formed
    -0.61
     Neighbor
    -0.60
    POSITIVE LOGITS
    chief
    0.90
     commander
    0.90
     stationed
    0.90
     colonel
    0.89
     commanders
    0.89
     Kham
    0.89
     commanding
    0.87
     Commander
    0.83
    utenant
    0.82
    stration
    0.81
    Activations Density 0.035%

    No Known Activations