© 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. 7-RES-JB
    11. 6919
    Prev
    Next
    INDEX
    Explanations

    mentions of time increments, specifically the word "minutes."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time durations, particularly minutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ashtra
    -0.81
    keye
    -0.81
    bard
    -0.80
    spons
    -0.80
    ãĤ©
    -0.78
    ded
    -0.76
    keyes
    -0.69
    Las
    -0.68
    rim
    -0.68
    yrinth
    -0.67
    POSITIVE LOGITS
     livest
    0.86
    hift
    0.85
    isters
    0.83
     Minutes
    0.83
    otaur
    0.82
    uters
    0.82
     ticking
    0.79
    neapolis
    0.79
     cooldown
    0.77
     lapse
    0.75
    Activations Density 0.030%

    No Known Activations