© 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. 10-RES-JB
    11. 10769
    Prev
    Next
    INDEX
    Explanations

    terms related to the aging process and elderly population

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aging and the elderly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ãĥ£
    -0.89
    vous
    -0.77
     CODE
    -0.71
    kell
    -0.70
    tyard
    -0.69
    anooga
    -0.68
    ãĥ
    -0.67
    rawdownloadcloneembedreportprint
    -0.67
    ãĥ¥
    -0.67
    lear
    -0.67
    POSITIVE LOGITS
     dementia
    1.02
     frail
    0.84
     population
    0.81
     gentleman
    0.77
     timers
    0.77
     Alzheimer
    0.74
    opausal
    0.73
     fashioned
    0.71
     ageing
    0.71
     citiz
    0.70
    Activations Density 0.069%

    No Known Activations