© 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. 6569
    Prev
    Next
    INDEX
    Explanations

    time-related words or phrases such as durations, durations, periods, and timelines

    oai_token-act-pair · gpt-3.5-turbo

    time-related references and durations

    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
    ħĭ
    -0.79
    rored
    -0.72
    Ü
    -0.70
    ¥µ
    -0.69
    edIn
    -0.66
    haps
    -0.63
    enture
    -0.62
    inav
    -0.62
    ²
    -0.61
    ociated
    -0.61
    POSITIVE LOGITS
     longer
    0.86
     to
    0.84
     convincing
    0.82
     elapsed
    0.74
     before
    0.69
     til
    0.64
     till
    0.64
     apiece
    0.63
     until
    0.62
     patiently
    0.62
    Activations Density 0.078%

    No Known Activations