© 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. 1-RES-JB
    11. 10228
    Prev
    Next
    INDEX
    Explanations

    phrases or abbreviations related to "NZ" (New Zealand)

    oai_token-act-pair · gpt-3.5-turbo

    references to New Zealand and its related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rooms
    -0.82
    lav
    -0.76
    Magikarp
    -0.75
    ible
    -0.73
    abet
    -0.73
    mot
    -0.72
     Dull
    -0.72
    flies
    -0.72
    rod
    -0.69
    ments
    -0.69
    POSITIVE LOGITS
     NZ
    1.40
     Zealand
    1.31
    NZ
    1.27
    XT
    1.05
     Auckland
    1.03
    uckland
    0.91
     Kiw
    0.88
     Wellington
    0.83
    nz
    0.82
     Canterbury
    0.79
    Activations Density 0.007%

    No Known Activations