© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11118
    Prev
    Next
    INDEX
    Explanations

    mentions of population sizes and densities, particularly regarding geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to population metrics and statistics

    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
    ery
    -0.78
    rah
    -0.78
    ĪĴ
    -0.73
    iate
    -0.71
    ippi
    -0.70
    eryl
    -0.68
    amina
    -0.67
    ryn
    -0.67
    inelli
    -0.66
    argon
    -0.66
    POSITIVE LOGITS
     density
    1.17
     growth
    0.95
     centers
    0.95
     dens
    0.92
    population
    0.90
     demographics
    0.89
     genetics
    0.87
    density
    0.87
     explosion
    0.86
     sizes
    0.85
    Activations Density 0.070%

    No Known Activations