© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 2584
    Prev
    Next
    INDEX
    Explanations

    dates and durations of time

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating the passage of time, specifically referencing years and decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    guyen
    -0.69
    eus
    -0.61
    natureconservancy
    -0.60
    icial
    -0.55
    hod
    -0.54
    inki
    -0.54
    Uncommon
    -0.52
     Converted
    -0.52
    bley
    -0.52
    Dialogue
    -0.51
    POSITIVE LOGITS
     now
    1.34
     already
    0.90
     ago
    0.88
     lately
    0.82
    now
    0.79
     NOW
    0.79
     without
    0.78
     uninterrupted
    0.77
     nowadays
    0.77
     awaiting
    0.74
    Activations Density 0.110%

    No Known Activations