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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 8651
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "multiple."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "multiple" or "variety."

    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
    ,—
    -0.77
    CHAPTER
    -0.77
    chief
    -0.74
    speak
    -0.72
     suppose
    -0.71
    morrow
    -0.71
    jud
    -0.68
    ogy
    -0.68
     ought
    -0.68
    boys
    -0.67
    POSITIVE LOGITS
     multiple
    3.15
    multiple
    2.74
     Multiple
    2.29
    Multiple
    2.15
     numerous
    1.82
     several
    1.59
     dozens
    1.57
     countless
    1.43
     multi
    1.37
     myriad
    1.34
    Activations Density 0.015%

    No Known Activations