© 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. 1-RES-JB
    11. 3563
    Prev
    Next
    INDEX
    Explanations

    phrases related to institutions or organizations, especially those with the word "National."

    oai_token-act-pair · gpt-3.5-turbo

    references to various national institutions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eva
    -0.78
    furt
    -0.74
    ÙĴ
    -0.73
    MODE
    -0.72
    ...]
    -0.72
    ppings
    -0.69
    enger
    -0.69
    ÃŁ
    -0.69
    ttes
    -0.67
    uble
    -0.67
    POSITIVE LOGITS
     Geographic
    0.94
     Legislative
    0.79
     Convention
    0.78
     Institute
    0.77
     Bureau
    0.75
     Highway
    0.74
     Institutes
    0.74
    wide
    0.74
    ité
    0.73
     Intelligence
    0.72
    Activations Density 0.023%

    No Known Activations