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. 4471
    Prev
    Next
    INDEX
    Explanations

    sentences with the word "while" followed by an action or observation happening simultaneously

    oai_token-act-pair · gpt-3.5-turbo

    the word "while," indicating a focus on concurrent actions or situations

    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
    pires
    -0.55
    alg
    -0.55
    eco
    -0.55
    omsday
    -0.55
    ":"/
    -0.53
    elong
    -0.52
     Perspect
    -0.51
     Exclusive
    -0.50
     inex
    -0.50
     itiner
    -0.50
    POSITIVE LOGITS
     while
    3.10
    while
    2.87
     whilst
    2.79
     whereas
    2.06
     although
    1.54
     While
    1.50
     despite
    1.40
    While
    1.38
     Whilst
    1.37
    despite
    1.19
    Activations Density 0.056%

    No Known Activations