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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 15914
    Prev
    Next
    INDEX
    Explanations

    phrases related to government authority and financial ratings

    oai_token-act-pair · gpt-3.5-turbo

    references to sovereign entities and concepts of sovereignty

    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
    OUT
    -0.78
    ograp
    -0.75
     Reyn
    -0.73
    iatus
    -0.71
    azine
    -0.70
    orah
    -0.65
     McGee
    -0.64
    oses
    -0.63
    DERR
    -0.63
     Hopkins
    -0.63
    POSITIVE LOGITS
     sovereign
    1.00
     immunity
    0.91
    ignty
    0.91
    ignt
    0.87
     decree
    0.83
     rights
    0.83
     allegiance
    0.82
     sovereignty
    0.80
     citizen
    0.79
     airspace
    0.78
    Activations Density 0.042%

    No Known Activations