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. 3-RES-JB
    6. 10490
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "today" in relation to various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the present day or current time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.80
    sym
    -0.78
    Sym
    -0.71
    imov
    -0.71
    alcohol
    -0.71
    chest
    -0.68
    henko
    -0.67
    aughed
    -0.66
    Chance
    -0.65
    sed
    -0.65
    POSITIVE LOGITS
    adays
    1.05
     morning
    0.97
     afternoon
    0.97
    days
    0.92
     Today
    0.88
    abouts
    0.84
     TODAY
    0.81
     evening
    0.78
     today
    0.77
     mornings
    0.77
    Activations Density 0.037%

    No Known Activations