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

    Neuronpedia

    Jacobian LensNEW
    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. 16690
    Prev
    Next
    INDEX
    Explanations

    references to time periods, specifically focusing on "few" days, weeks, months, or years

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time, particularly phrases involving "few" often indicating recent events or changes

    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
    Winner
    -0.75
    obal
    -0.68
    rawdownloadcloneembedreportprint
    -0.67
    ater
    -0.65
    ikini
    -0.64
    wrapper
    -0.64
    aughter
    -0.63
    winner
    -0.63
    racuse
    -0.62
    gow
    -0.62
    POSITIVE LOGITS
     weeks
    1.79
     months
    1.74
     years
    1.62
     days
    1.59
     decades
    1.42
    months
    1.39
     paragraphs
    1.31
    years
    1.31
     hundred
    1.29
     hours
    1.28
    Activations Density 0.060%

    No Known Activations