© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20738
    Prev
    Next
    INDEX
    Explanations

    keywords related to government social welfare programs and health insurance

    oai_token-act-pair · gpt-3.5-turbo

    references to social welfare programs and health insurance

    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
    USS
    -0.82
    ãĤ¨ãĥ«
    -0.74
    GMT
    -0.74
    OTE
    -0.73
     attm
    -0.72
    UMP
    -0.72
    ERG
    -0.69
     Obj
    -0.67
    rez
    -0.65
    ISS
    -0.65
    POSITIVE LOGITS
    amacare
    0.95
     premiums
    0.87
     clinic
    0.86
     insurance
    0.85
     childbirth
    0.85
     healthcare
    0.85
     clinics
    0.84
     medications
    0.84
     providers
    0.84
     caregivers
    0.83
    Activations Density 0.294%

    No Known Activations