© 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. 3-RES-JB
    11. 12948
    Prev
    Next
    INDEX
    Explanations

    mentions of daily activities or routines

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "daily"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holes
    -0.86
    aine
    -0.81
    artisan
    -0.81
    eer
    -0.81
    dinand
    -0.78
    atchewan
    -0.76
    OHN
    -0.75
    essee
    -0.73
    hole
    -0.72
    ARP
    -0.72
    POSITIVE LOGITS
    motion
    0.93
     daily
    0.88
     commute
    0.84
     occurrence
    0.84
     intervals
    0.83
     upkeep
    0.83
     necessities
    0.83
     ration
    0.80
     weekday
    0.80
     routines
    0.79
    Activations Density 0.013%

    No Known Activations