© 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 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. 10-RES-JB
    11. 4424
    Prev
    Next
    INDEX
    Explanations

    information related to populations and demographics of different countries

    oai_token-act-pair · gpt-3.5-turbo
    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
    inventoryQuantity
    -0.71
     fiasco
    -0.71
     remedies
    -0.71
     pitfalls
    -0.70
     teamwork
    -0.67
     deadlines
    -0.67
     Trials
    -0.67
    inelli
    -0.65
     optimizations
    -0.65
    prints
    -0.65
    POSITIVE LOGITS
     population
    1.36
     inhabitants
    1.28
    population
    1.15
    Population
    1.12
     inhab
    1.08
     inhabit
    1.07
     Population
    1.02
     residing
    1.02
     households
    0.98
     populace
    0.98
    Activations Density 0.311%

    No Known Activations