© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 8018
    Prev
    Next
    INDEX
    Explanations

    references to countries or regions in the Americas

    oai_token-act-pair · gpt-3.5-turbo

    references to Latin America and its geographical context

    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
    soon
    -0.75
     fences
    -0.72
    emetery
    -0.69
    puter
    -0.68
    heed
    -0.63
    NK
    -0.63
     boun
    -0.62
    liners
    -0.62
    endiary
    -0.60
    bledon
    -0.59
    POSITIVE LOGITS
    xia
    0.92
    uria
    0.79
     continent
    0.75
    furt
    0.75
    ternity
    0.72
     Basin
    0.71
     Incarn
    0.71
    alis
    0.70
    lio
    0.70
    igraph
    0.70
    Activations Density 0.034%

    No Known Activations