© 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. 2-RES-JB
    11. 21437
    Prev
    Next
    INDEX
    Explanations

    references to social welfare programs and policies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to public assistance and welfare programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orp
    -0.73
    NK
    -0.70
     pus
    -0.70
     Petr
    -0.69
    Jess
    -0.68
     Moment
    -0.68
    Tact
    -0.68
     thunder
    -0.66
     Laurent
    -0.66
    peror
    -0.64
    POSITIVE LOGITS
     welfare
    1.11
    elfare
    1.09
     paycheck
    1.08
     allowance
    1.06
     subsistence
    1.01
     visas
    1.01
     uninsured
    0.99
     incomes
    0.96
     childcare
    0.96
     earners
    0.96
    Activations Density 0.837%

    No Known Activations