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. 8-RES-JB
    6. 9593
    Prev
    Next
    INDEX
    Explanations

    references to wealthy individuals, social classes or economic status

    oai_token-act-pair · gpt-3.5-turbo

    references to wealth and wealthy individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uality
    -0.97
    uberty
    -0.85
    DOC
    -0.79
    bsp
    -0.73
    stress
    -0.73
    PRESS
    -0.69
    ña
    -0.68
    urgy
    -0.68
    idine
    -0.66
    otide
    -0.66
    POSITIVE LOGITS
     earners
    0.98
     Asians
    0.90
     donors
    0.90
     landowners
    0.86
     individuals
    0.84
     businessmen
    0.84
     retirees
    0.83
     Institution
    0.83
     citiz
    0.82
     patrons
    0.81
    Activations Density 0.049%

    No Known Activations