© 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. 0-RES-JB
    11. 16988
    Prev
    Next
    INDEX
    Explanations

    references to wealth and economic disparities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "rich" and its associations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amar
    -0.70
    counter
    -0.70
    udence
    -0.68
    bolt
    -0.67
     Shuttle
    -0.67
    mast
    -0.67
    ITNESS
    -0.66
    oulder
    -0.66
    :(
    -0.64
    breaker
    -0.64
    POSITIVE LOGITS
     rich
    3.70
     richer
    2.79
     wealthy
    2.14
     richest
    2.08
    rich
    2.04
     wealthier
    1.75
     richness
    1.74
    Rich
    1.65
     Rich
    1.65
     enriched
    1.63
    Activations Density 0.019%

    No Known Activations