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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3670
    Prev
    Next
    INDEX
    Explanations

    information related to demographics, such as age, gender, education, income, and ethnicity

    oai_token-act-pair · gpt-3.5-turbo

    references to demographic factors influencing income and related variables

    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
    mud
    -0.77
     Canaver
    -0.69
    ertodd
    -0.68
    pired
    -0.68
    prus
    -0.68
    bara
    -0.68
    annon
    -0.67
    aird
    -0.67
    awaited
    -0.66
    cour
    -0.64
    POSITIVE LOGITS
     preferences
    1.07
     preference
    0.98
     affiliation
    0.95
     characteristics
    0.94
     severity
    0.92
     specificity
    0.88
     composition
    0.82
     Quantity
    0.82
     availability
    0.82
     affili
    0.82
    Activations Density 0.315%

    No Known Activations