© 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. 1-RES-JB
    11. 7461
    Prev
    Next
    INDEX
    Explanations

    Polish last names, specifically ending in '-owski'

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those ending in 'owski' or 'ewski'

    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
    Ü
    -0.70
    ãĥ¼ãĥ³
    -0.69
     Haitian
    -0.68
     اÙĦ
    -0.65
    ãĥ¼ãĥĨ
    -0.62
    ridges
    -0.62
     Coastal
    -0.61
    eral
    -0.61
    fully
    -0.59
     Pastebin
    -0.59
    POSITIVE LOGITS
    owski
    1.32
    inski
    0.95
    chuk
    0.89
    enegger
    0.87
    owsky
    0.85
    itsch
    0.83
    zyk
    0.82
    ynski
    0.82
    ski
    0.82
    ewski
    0.82
    Activations Density 0.006%

    No Known Activations