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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 22581
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to economic classes and demographics, particularly focusing on the middle class

    oai_token-act-pair · gpt-3.5-turbo

    references to middle-class socioeconomic status

    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
    pload
    -0.81
     Canaver
    -0.71
    ongyang
    -0.71
    ļéĨĴ
    -0.70
     simul
    -0.70
    kson
    -0.69
    aila
    -0.65
     Shutterstock
    -0.64
    endum
    -0.64
     Sawyer
    -0.63
    POSITIVE LOGITS
    tier
    1.09
    level
    1.00
    aged
    0.99
    class
    0.95
    earth
    0.92
    income
    0.91
    school
    0.90
    of
    0.90
    leaning
    0.87
    ranking
    0.86
    Activations Density 0.044%

    No Known Activations