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. 4-RES-JB
    6. 8330
    Prev
    Next
    INDEX
    Explanations

    mentions of financial situations or economic status, particularly relating to lower income levels

    oai_token-act-pair · gpt-3.5-turbo

    references to low-income individuals and families

    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
    AMS
    -0.76
    andal
    -0.75
    andals
    -0.74
    è¦ļéĨĴ
    -0.74
    lain
    -0.74
    OY
    -0.73
    в
    -0.70
    ãĤ¨ãĥ«
    -0.70
    =-=-=-=-
    -0.69
    umm
    -0.69
    POSITIVE LOGITS
     earners
    1.47
     income
    0.94
     Income
    0.86
     mobility
    0.85
     incomes
    0.82
     poverty
    0.82
     disparity
    0.78
    income
    0.78
     inequality
    0.77
     unemploy
    0.76
    Activations Density 0.012%

    No Known Activations