© 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. 11616
    Prev
    Next
    INDEX
    Explanations

    terms related to social welfare programs

    oai_token-act-pair · gpt-3.5-turbo

    references to social programs, particularly Social Security

    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
    nces
    -0.80
    sets
    -0.73
     Kinnikuman
    -0.70
    xual
    -0.68
    1001
    -0.62
    rawdownloadcloneembedreportprint
    -0.62
    20439
    -0.62
    lists
    -0.60
    ller
    -0.60
    umping
    -0.60
    POSITIVE LOGITS
     welfare
    0.95
     Welfare
    0.88
     democr
    0.82
    ized
    0.81
    istic
    0.79
     welf
    0.78
    ists
    0.77
     Security
    0.77
     Justice
    0.77
     conservatives
    0.76
    Activations Density 0.025%

    No Known Activations