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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13358
    Prev
    Next
    INDEX
    Explanations

    references to sovereignty or sovereign entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "sovereign" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UNCH
    -0.87
    orah
    -0.75
     Hopkins
    -0.73
    OUT
    -0.73
    oles
    -0.72
    ACK
    -0.71
    xxxxxxxx
    -0.70
    acha
    -0.70
     Indust
    -0.70
     McGee
    -0.69
    POSITIVE LOGITS
     sovereign
    0.90
     immunity
    0.87
    iazep
    0.78
     monarch
    0.78
     citizen
    0.78
    sburg
    0.77
     decree
    0.76
     nomine
    0.76
    s
    0.74
    911
    0.74
    Activations Density 0.013%

    No Known Activations