© 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. 2955
    Prev
    Next
    INDEX
    Explanations

    terms related to social welfare, poverty, and marginalized groups

    oai_token-act-pair · gpt-3.5-turbo

    references to marginalized groups and social justice issues

    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
     Carbuncle
    -0.88
    forcement
    -0.85
    Reviewer
    -0.78
     VIDEOS
    -0.77
    DAQ
    -0.76
    ciation
    -0.73
    emonium
    -0.71
    spection
    -0.69
    forcer
    -0.67
    ezvous
    -0.66
    POSITIVE LOGITS
     elderly
    1.52
     disadvantaged
    1.49
     unemployed
    1.48
     disabled
    1.44
     minorities
    1.44
     marginalized
    1.33
     retirees
    1.30
     uninsured
    1.25
     oppressed
    1.24
     needy
    1.24
    Activations Density 0.220%

    No Known Activations