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. 14199
    Prev
    Next
    INDEX
    Explanations

    specific phrases beginning with the word "Some"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Some" indicating a significant context or statement being made

    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
     inclusive
    -0.67
     equivalent
    -0.63
     supporting
    -0.63
     combined
    -0.63
     mark
    -0.62
     consum
    -0.62
     pal
    -0.62
     serving
    -0.62
     nor
    -0.61
     epit
    -0.61
    POSITIVE LOGITS
    Some
    2.85
    Many
    2.04
    Others
    1.93
     Some
    1.88
    some
    1.88
    Sometimes
    1.83
    Several
    1.83
    Certain
    1.77
    Most
    1.76
     SOME
    1.67
    Activations Density 0.019%

    No Known Activations