Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23466
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "so" used to indicate consequences or implications

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "so" used to connect thoughts or ideas

    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
    intosh
    -0.75
    adelphia
    -0.67
    ELD
    -0.62
    miah
    -0.62
    Rated
    -0.61
    MpServer
    -0.60
    saf
    -0.60
    ety
    -0.59
    roma
    -0.59
    tec
    -0.59
    POSITIVE LOGITS
    oner
    1.17
     why
    1.11
     beware
    1.08
     congr
    0.98
     hopefully
    0.97
     naturally
    0.96
     yeah
    0.96
     maybe
    0.93
     congratulations
    0.92
     please
    0.91
    Activations Density 0.074%

    No Known Activations