© 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. 2-RES-JB
    11. 10458
    Prev
    Next
    INDEX
    Explanations

    terms related to bureaucratic systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bureaucracy and administrative systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    words
    -0.85
    posed
    -0.81
    topic
    -0.78
    alone
    -0.73
    stocks
    -0.72
    lihood
    -0.71
    eele
    -0.70
    points
    -0.69
    aired
    -0.67
    inent
    -0.66
    POSITIVE LOGITS
     bureaucracy
    1.38
     bureaucrats
    1.14
     bureaucr
    1.10
     bureaucratic
    1.02
     unnecess
    0.84
     paperwork
    0.83
     duplication
    0.83
     jargon
    0.82
     conflic
    0.80
     complexity
    0.78
    Activations Density 0.016%

    No Known Activations