© 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. 8-RES-JB
    11. 157
    Prev
    Next
    INDEX
    Explanations

    keywords related to "Social Security"

    oai_token-act-pair · gpt-3.5-turbo

    references to Social Security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcs
    -0.89
    GMT
    -0.84
    ãĥ£
    -0.79
     Nath
    -0.75
    phas
    -0.75
    yond
    -0.73
    GBT
    -0.73
     ener
    -0.71
    ²¾
    -0.71
    chance
    -0.70
    POSITIVE LOGITS
     Disability
    1.20
     Administration
    1.17
     disability
    0.97
     Retirement
    0.97
     Loan
    0.89
    eteria
    0.85
     trustees
    0.84
     Contributions
    0.82
     Compensation
    0.81
     Income
    0.80
    Activations Density 0.037%

    No Known Activations