© 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. 11-RES-JB
    11. 17071
    Prev
    Next
    INDEX
    Explanations

    terms related to financial and political matters, such as banking, government, taxes, policies, and reports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to finance, government, and cultural topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Houston
    -0.73
     Houston
    -0.70
     Pittsburgh
    -0.67
     Baltimore
    -0.66
     Louisville
    -0.65
     Seattle
    -0.64
     Cleveland
    -0.63
     Vegas
    -0.63
     Maryland
    -0.63
    ModLoader
    -0.62
    POSITIVE LOGITS
     diplomat
    0.77
     abroad
    0.76
     ambassador
    0.76
    isine
    0.75
    smanship
    0.71
    wings
    0.71
     surn
    0.70
    pora
    0.69
    orate
    0.68
    arel
    0.68
    Activations Density 0.512%

    No Known Activations