© 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. 8-RES-JB
    11. 7791
    Prev
    Next
    INDEX
    Explanations

    terms related to government social welfare programs, particularly Social Security

    oai_token-act-pair · gpt-3.5-turbo

    references to social security and related policies

    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
    nces
    -0.80
    oning
    -0.71
    oned
    -0.69
    llers
    -0.66
    ously
    -0.64
    1001
    -0.64
    xual
    -0.63
     landfall
    -0.63
    peed
    -0.63
     needless
    -0.62
    POSITIVE LOGITS
    Health
    0.81
     Insurance
    0.77
    Flow
    0.76
    ists
    0.75
     Welfare
    0.74
    nect
    0.74
    ized
    0.74
     Security
    0.73
     welfare
    0.72
    ité
    0.71
    Activations Density 0.019%

    No Known Activations