© 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. 17456
    Prev
    Next
    INDEX
    Explanations

    phrases related to time durations or intervals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of time periods, specifically weeks and related qualifiers

    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
    AI
    -0.87
     Liang
    -0.87
     Ariel
    -0.81
     Azure
    -0.78
    anus
    -0.77
    Sil
    -0.73
     Assass
    -0.72
    hei
    -0.71
    aic
    -0.71
    agall
    -0.70
    POSITIVE LOGITS
     week
    1.57
     Week
    1.51
    week
    1.50
    Week
    1.44
     WEEK
    1.42
     Weeks
    1.36
     weeks
    1.34
     fortnight
    1.07
     weekly
    1.00
     Thurs
    0.95
    Activations Density 0.135%

    No Known Activations