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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 935
    Prev
    Next
    INDEX
    Explanations

    the term "sovereignty"

    oai_token-act-pair · gpt-4-turbo

    mentions of national sovereignty, particularly in the context of violations or assertions of it

    oai_token-act-pair · gpt-3.5-turbo

    references to sovereignty

    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
     Alto
    -0.82
    ogene
    -0.75
    ches
    -0.72
    ched
    -0.68
    ORN
    -0.68
    hematic
    -0.67
     DeV
    -0.67
    TER
    -0.66
    ergy
    -0.66
     Hoffman
    -0.65
    POSITIVE LOGITS
    ignty
    1.49
     sovereignty
    1.03
     Sovere
    0.95
    ignt
    0.90
     sovere
    0.89
     minded
    0.76
     sovereign
    0.76
     decree
    0.74
     droid
    0.74
     nomine
    0.73
    Activations Density 0.008%

    No Known Activations