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. 3-RES-JB
    6. 22150
    Prev
    Next
    INDEX
    Explanations

    terms related to social welfare programs, particularly Social Security

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social welfare programs, particularly Social Security

    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
    Äĩ
    -0.83
    20439
    -0.73
    nces
    -0.72
    icular
    -0.70
    xual
    -0.69
     needless
    -0.67
     ridden
    -0.67
    upon
    -0.63
    llers
    -0.63
    pless
    -0.62
    POSITIVE LOGITS
    ists
    0.80
    Aff
    0.79
    Health
    0.76
    Flow
    0.76
     Responsibility
    0.76
    Works
    0.74
     Security
    0.74
    Work
    0.73
     Equality
    0.73
    Social
    0.72
    Activations Density 0.010%

    No Known Activations