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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 16691
    Prev
    Next
    INDEX
    Explanations

    terms related to social issues, specifically focusing on youth-related problems and community support programs

    oai_token-act-pair · gpt-3.5-turbo

    topics related to youth issues and support initiatives

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

    No Comments

    Negative Logits
    peror
    -0.86
    canon
    -0.81
    emonium
    -0.81
    orp
    -0.76
    ULE
    -0.72
    witz
    -0.72
    tre
    -0.69
    ocular
    -0.69
    ebus
    -0.69
    hot
    -0.68
    POSITIVE LOGITS
     disproportionately
    1.04
     homelessness
    1.03
     populations
    1.00
     outreach
    0.98
     prevention
    0.95
     welfare
    0.93
     disadvantaged
    0.93
     healthcare
    0.92
     workforce
    0.91
     Medicaid
    0.91
    Activations Density 0.728%

    No Known Activations