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. 11-RES-JB
    6. 23609
    Prev
    Next
    INDEX
    Explanations

    words related to the passage of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating necessity, urgency, and the state of being or condition of subjects discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resil
    -0.77
     havoc
    -0.71
     shenan
    -0.58
    ERY
    -0.57
    âĸ¬
    -0.56
    ongh
    -0.55
     prism
    -0.54
     choir
    -0.53
    Buzz
    -0.53
     frenzy
    -0.52
    POSITIVE LOGITS
     for
    0.94
    for
    0.88
    between
    0.79
     arising
    0.77
     arise
    0.75
     regarding
    0.74
    piring
    0.70
     arises
    0.70
     to
    0.69
    izons
    0.68
    Activations Density 0.405%

    No Known Activations