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. 12-RES-JB
    6. 6924
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and economic justice and interaction between government, business, and the community

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to social business initiatives and their impact on economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.92
    ĸļ士
    -0.85
    ÃįÃį
    -0.84
    Þ
    -0.79
    ħĭ
    -0.79
    ñ
    -0.78
    Ô
    -0.77
    inventoryQuantity
    -0.77
    ãĥ¯ãĥ³
    -0.76
    milo
    -0.74
    POSITIVE LOGITS
     things
    0.71
     everywhere
    0.70
     stuff
    0.68
     everybody
    0.67
     everything
    0.63
     wherever
    0.63
     help
    0.60
     all
    0.60
     lots
    0.59
     everyone
    0.59
    Activations Density 0.971%

    No Known Activations