© 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. 4-RES-JB
    11. 7033
    Prev
    Next
    INDEX
    Explanations

    words related to the process of aging

    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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fax
    -0.80
    kie
    -0.75
    ãĥ£
    -0.74
    kell
    -0.73
    ª
    -0.73
    arel
    -0.73
    cluding
    -0.70
    agram
    -0.69
    zzle
    -0.69
    lear
    -0.69
    POSITIVE LOGITS
     ageing
    0.87
     aging
    0.83
     timers
    0.80
     dementia
    0.80
    timer
    0.77
     sen
    0.77
     Aging
    0.76
     timer
    0.74
     therap
    0.73
    escent
    0.71
    Activations Density 0.011%

    No Known Activations