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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 18200
    Prev
    Next
    INDEX
    Explanations

    words related to age, especially elderly ages

    oai_token-act-pair · gpt-3.5-turbo

    mentions of age, specifically focusing on elderly individuals

    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
    ËĪ
    -0.85
    ileaks
    -0.81
    inventoryQuantity
    -0.80
    ipedia
    -0.80
    aucus
    -0.80
     mathemat
    -0.79
    icter
    -0.79
    pecially
    -0.77
    ettings
    -0.77
    okin
    -0.76
    POSITIVE LOGITS
     Frenchman
    0.78
     Bernard
    0.74
     man
    0.73
     refrain
    0.68
     Samar
    0.68
     widow
    0.68
     Rite
    0.67
     Victorian
    0.67
     York
    0.66
     Pagan
    0.66
    Activations Density 0.024%

    No Known Activations