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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 174
    Prev
    Next
    INDEX
    Explanations

    terms related to social welfare programs such as Social Security

    oai_token-act-pair · gpt-3.5-turbo

    references to social programs and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ell
    -0.76
    aine
    -0.75
    oly
    -0.75
    alling
    -0.72
     probe
    -0.70
    elle
    -0.66
     flown
    -0.66
     rod
    -0.65
     probes
    -0.65
     bulb
    -0.64
    POSITIVE LOGITS
     Social
    3.71
    Social
    2.72
    social
    2.22
     social
    1.94
     Socialism
    1.57
     Soci
    1.54
    ocial
    1.54
     Socialist
    1.46
     socially
    1.37
     Welfare
    1.27
    Activations Density 0.008%

    No Known Activations