© 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. 8586
    Prev
    Next
    INDEX
    Explanations

    phrases related to socioeconomic inequality

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of inequality, including economic and social disparities

    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
    ITNESS
    -0.84
    cise
    -0.82
    ullivan
    -0.80
    stanbul
    -0.73
    dit
    -0.69
    ishable
    -0.69
     refresh
    -0.68
    ittee
    -0.67
    uscript
    -0.66
    Elect
    -0.65
    POSITIVE LOGITS
     plag
    1.46
     endemic
    1.27
     perpetrated
    1.15
     epidemic
    1.14
     prevalent
    1.11
     rampant
    1.09
     rife
    1.06
     perv
    0.98
     affecting
    0.96
     exacerbated
    0.96
    Activations Density 0.234%

    No Known Activations