© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 11221
    Prev
    Next
    INDEX
    Explanations

    mentions of wealthy individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    terms related to wealth and affluent individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uberty
    -0.86
    uality
    -0.81
    ña
    -0.80
    yrinth
    -0.76
    urgy
    -0.70
    TAG
    -0.69
    TYPE
    -0.68
    DOC
    -0.68
    bsp
    -0.67
    Temperature
    -0.67
    POSITIVE LOGITS
     donors
    1.05
     businessman
    1.03
     philanthrop
    1.02
     benef
    1.01
     landowners
    0.98
     businessmen
    0.97
     donor
    0.91
     wealthy
    0.88
     billionaires
    0.87
     earners
    0.86
    Activations Density 0.059%

    No Known Activations