© 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. 7281
    Prev
    Next
    INDEX
    Explanations

    mentions of bureaucracy or bureaucratic terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bureaucracy and its complexities

    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
    words
    -0.94
    eele
    -0.90
    alone
    -0.84
    posed
    -0.76
    ints
    -0.73
    lihood
    -0.73
    water
    -0.73
    aired
    -0.71
    topic
    -0.70
     Emin
    -0.70
    POSITIVE LOGITS
     bureaucracy
    1.24
     bureaucr
    1.15
     bureaucrats
    1.09
     bureaucratic
    0.99
     jargon
    0.85
     machinery
    0.84
     unnecess
    0.84
     paperwork
    0.75
     councill
    0.74
     bung
    0.73
    Activations Density 0.019%

    No Known Activations