© 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. 12952
    Prev
    Next
    INDEX
    Explanations

    keywords related to the size and status of different populations, particularly in terms of species or demographic groups

    oai_token-act-pair · gpt-3.5-turbo

    references to populations, particularly in the context of species or demographics

    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
    nit
    -0.86
    cer
    -0.77
    sbm
    -0.74
    ibur
    -0.73
    rav
    -0.73
    NRS
    -0.73
    NB
    -0.72
    ny
    -0.70
    Accessory
    -0.70
    neg
    -0.69
    POSITIVE LOGITS
     populations
    1.26
     inhab
    0.82
     genomes
    0.82
     cultures
    0.78
     markets
    0.77
     population
    0.77
     mosquit
    0.77
     unemploy
    0.76
     distributions
    0.76
     capitals
    0.75
    Activations Density 0.008%

    No Known Activations