© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 12649
    Prev
    Next
    INDEX
    Explanations

    comparisons between different economic and social groups

    oai_token-act-pair · gpt-3.5-turbo

    data related to income inequality and statistics regarding socioeconomic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mosqu
    -0.97
    answered
    -0.88
    £ı
    -0.85
     Atomic
    -0.77
     caut
    -0.75
     Klingon
    -0.75
     Bullets
    -0.74
    cone
    -0.73
    request
    -0.73
    Ul
    -0.72
    POSITIVE LOGITS
     inequality
    1.88
     poverty
    1.66
     incomes
    1.65
     wealth
    1.61
     richest
    1.60
     inequalities
    1.58
     wealthiest
    1.57
     income
    1.52
    equality
    1.49
     wealthier
    1.48
    Activations Density 0.512%

    No Known Activations