© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11816
    Prev
    Next
    INDEX
    Explanations

    concepts related to time duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating duration or a period of time

    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
    eteria
    -0.68
    stood
    -0.65
    artisan
    -0.62
     resemblance
    -0.61
    ãĤ¨
    -0.61
    ution
    -0.59
     Hood
    -0.59
     Proceed
    -0.59
    ffen
    -0.59
     Spoiler
    -0.58
    POSITIVE LOGITS
     months
    1.56
    months
    1.54
     weeks
    1.53
    years
    1.40
     years
    1.37
     decades
    1.32
     Months
    1.30
     days
    1.30
     centuries
    1.26
     nights
    1.24
    Activations Density 0.092%

    No Known Activations