Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 190
    Prev
    Next
    INDEX
    Explanations

    the word "sovereign" or related to sovereign entities or concepts

    oai_token-act-pair · gpt-4-turbo

    terms related to political sovereignty and authority

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sovereignty and sovereign authority

    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
    OUT
    -0.87
    UNCH
    -0.81
    xxxxxxxx
    -0.77
    xx
    -0.73
    chel
    -0.73
    ACK
    -0.71
     Hopkins
    -0.71
    oles
    -0.70
    OST
    -0.70
    ches
    -0.70
    POSITIVE LOGITS
     sovereign
    1.08
     immunity
    0.92
     Sovereign
    0.82
     monarch
    0.79
    ignty
    0.79
     citizen
    0.77
     issuer
    0.76
    icter
    0.76
     citiz
    0.76
     asset
    0.74
    Activations Density 0.008%

    No Known Activations