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

    Neuronpedia

    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. 0-RES-JB
    11. 20210
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Chile."

    oai_token-act-pair · gpt-3.5-turbo

    references to Chile and related geographical identifiers

    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
     inn
    -0.78
    auder
    -0.73
     ///
    -0.70
    Ry
    -0.67
    Donnell
    -0.66
     Inn
    -0.63
    ////////////////
    -0.63
    ayn
    -0.62
    ohn
    -0.62
    KB
    -0.62
    POSITIVE LOGITS
     Chile
    3.90
     Chilean
    3.13
     Santiago
    2.16
     Peru
    1.95
     Paragu
    1.92
     Bolivia
    1.91
     Uruguay
    1.89
     Argentina
    1.85
     Guatemala
    1.72
     Argentine
    1.68
    Activations Density 0.021%

    No Known Activations