Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14225
    Prev
    Next
    INDEX
    Explanations

    terms related to government assistance programs, especially those related to financial support like food stamps and Temporary Assistance for Needy Families (TANF)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government assistance programs and support for families in need

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ul
    -0.75
    Appearance
    -0.73
    Ô
    -0.73
     Veh
    -0.71
    USS
    -0.70
     Laurent
    -0.68
    NK
    -0.68
    GMT
    -0.67
    ItemImage
    -0.66
    ãĥĦ
    -0.66
    POSITIVE LOGITS
    elfare
    1.09
     allowance
    1.02
     entitle
    1.00
     parole
    0.91
     vouchers
    0.91
     Disability
    0.89
     welfare
    0.88
     entitlement
    0.86
     paycheck
    0.84
     provisions
    0.84
    Activations Density 0.140%

    No Known Activations