© 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. 10-RES-JB
    11. 16118
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental and organizational restructuring or control

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to government and military institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frequent
    -0.68
    \":
    -0.62
     inducing
    -0.61
    quickShipAvailable
    -0.61
     extremes
    -0.60
     occasional
    -0.60
     encour
    -0.60
    hots
    -0.59
    assion
    -0.59
     ingestion
    -0.59
    POSITIVE LOGITS
     finances
    1.03
     bureaucracy
    0.94
     workforce
    0.93
     altogether
    0.91
     presidency
    0.87
     apparatus
    0.85
     coffers
    0.84
     empire
    0.82
    's
    0.82
     indefinitely
    0.81
    Activations Density 0.369%

    No Known Activations