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. 14121
    Prev
    Next
    INDEX
    Explanations

    words related to global issues or events

    oai_token-act-pair · gpt-3.5-turbo

    references to global issues or phenomena

    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
    atto
    -0.78
    ,—
    -0.76
    bay
    -0.73
    enes
    -0.71
    reau
    -0.70
    rats
    -0.68
    autions
    -0.68
     Cemetery
    -0.68
    amiya
    -0.67
     Pros
    -0.67
    POSITIVE LOGITS
     global
    3.42
    global
    2.80
    Global
    2.50
     globally
    2.49
     Global
    2.40
     worldwide
    2.16
     globalization
    1.98
     international
    1.84
     geopolitical
    1.52
     multinational
    1.51
    Activations Density 0.022%

    No Known Activations