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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 20547
    Prev
    Next
    INDEX
    Explanations

    phrases related to duration or time periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time duration or periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arts
    -0.71
     disrespect
    -0.57
     Favorite
    -0.57
    Ü
    -0.56
    pb
    -0.56
    artisan
    -0.55
    ãĤ´
    -0.55
     kindred
    -0.55
    Chair
    -0.54
    girls
    -0.52
    POSITIVE LOGITS
     duration
    1.25
     longer
    1.22
     period
    1.13
     periods
    1.12
     indefinite
    1.11
     lifetime
    1.07
     eternity
    1.03
     indefinitely
    0.99
     lifespan
    0.98
     foreseeable
    0.96
    Activations Density 0.213%

    No Known Activations