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. 5671
    Prev
    Next
    INDEX
    Explanations

    terms related to wealth and economic concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to wealth and economic disparity

    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
     externalToEVAOnly
    -0.69
    cers
    -0.66
    ãģ¦
    -0.65
    £ı
    -0.63
     Yel
    -0.63
    ople
    -0.62
     sshd
    -0.61
    Earth
    -0.61
     Blaz
    -0.61
    WER
    -0.61
    POSITIVE LOGITS
     wealth
    1.00
     redistribution
    0.96
     inequality
    0.95
     amassed
    0.95
     accumulation
    0.95
     holdings
    0.93
     trove
    0.92
     disparity
    0.90
     accumulated
    0.88
     disparities
    0.83
    Activations Density 0.046%

    No Known Activations