Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 18218
    Prev
    Next
    INDEX
    Explanations

    words related to the theme of aging

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to aging and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kie
    -0.86
    tyard
    -0.83
    ãĥ£
    -0.83
     Bundy
    -0.80
    ª
    -0.80
    toe
    -0.74
    kell
    -0.73
    ilda
    -0.72
    bley
    -0.72
    TRY
    -0.72
    POSITIVE LOGITS
     ageing
    0.90
     aging
    0.87
     timers
    0.83
     dementia
    0.81
     onset
    0.81
     decay
    0.78
     baggage
    0.76
    escent
    0.75
     sen
    0.75
     cohorts
    0.73
    Activations Density 0.029%

    No Known Activations