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. 0-RES-JB
    6. 23577
    Prev
    Next
    INDEX
    Explanations

    words containing the substring "now"

    oai_token-act-pair · gpt-3.5-turbo

    the word "now" and its variations, indicating urgency or immediacy

    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
     isolation
    -0.61
     MFT
    -0.61
     Pascal
    -0.57
     solo
    -0.57
     jar
    -0.56
     appet
    -0.56
     cultures
    -0.55
     adherence
    -0.55
     Kardashian
    -0.54
     labor
    -0.54
    POSITIVE LOGITS
    now
    4.37
    today
    1.94
    soon
    1.79
    NOW
    1.72
    later
    1.71
    then
    1.65
    still
    1.49
    Now
    1.47
    formerly
    1.36
     now
    1.35
    Activations Density 0.008%

    No Known Activations