© 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. 11-RES-JB
    11. 7564
    Prev
    Next
    INDEX
    Explanations

    phrases related to the elderly and aging, including medical concerns and social policies targeting this demographic

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the elderly population and their associated conditions or issues

    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
    åŃ
    -0.76
    ãĥ£
    -0.74
     Parsons
    -0.67
    ramid
    -0.67
    é¾
    -0.66
    lez
    -0.65
     CODE
    -0.65
    ãĥ
    -0.65
    eele
    -0.62
    kell
    -0.61
    POSITIVE LOGITS
     dementia
    1.18
     Alzheimer
    0.92
     frail
    0.86
     dement
    0.82
     grandmother
    0.75
     sickness
    0.75
     population
    0.73
     retire
    0.72
     citiz
    0.72
     widow
    0.72
    Activations Density 0.110%

    No Known Activations