© 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. 6325
    Prev
    Next
    INDEX
    Explanations

    mentions of durations of time, such as years and months

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations, particularly the word "years" and similar phrases

    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
    notice
    -0.88
    inki
    -0.78
    egu
    -0.75
    oops
    -0.72
    emort
    -0.71
    depth
    -0.71
    itely
    -0.70
    Grade
    -0.70
    Notice
    -0.68
    cair
    -0.67
    POSITIVE LOGITS
     ago
    0.81
     observers
    0.77
     commentators
    0.75
     economists
    0.74
     now
    0.72
     pundits
    0.72
     historians
    0.71
     thereafter
    0.71
     critics
    0.69
     we
    0.69
    Activations Density 0.096%

    No Known Activations