© 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. 3154
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passing of time, specifically the duration of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to durations of time, particularly years and months

    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
    ibrary
    -0.66
    este
    -0.64
    Leaks
    -0.64
    ople
    -0.63
     slightest
    -0.59
     contag
    -0.59
    anooga
    -0.59
    eston
    -0.58
    eus
    -0.57
    ash
    -0.56
    POSITIVE LOGITS
     ago
    1.39
     Ago
    1.19
     olds
    1.13
    manship
    0.97
    '
    0.94
     consecut
    0.92
     worth
    0.91
     apiece
    0.90
    hips
    0.81
    ago
    0.80
    Activations Density 0.114%

    No Known Activations