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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 10129
    Prev
    Next
    INDEX
    Explanations

    mentions of specific countries, with a focus on New Zealand

    oai_token-act-pair · gpt-3.5-turbo

    references to New Zealand in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    Denver
    -0.76
    baugh
    -0.71
    chel
    -0.69
    CLOSE
    -0.69
     Yel
    -0.68
    <<
    -0.66
    older
    -0.66
    osure
    -0.66
    м
    -0.66
    Ky
    -0.63
    POSITIVE LOGITS
     Zealand
    1.16
     Territories
    1.07
    XT
    0.99
     Herald
    0.97
     Samoa
    0.93
    istani
    0.89
    ers
    0.88
     Airlines
    0.85
     Auckland
    0.84
     Islands
    0.84
    Activations Density 0.041%

    No Known Activations