© 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. 11294
    Prev
    Next
    INDEX
    Explanations

    time periods mentioned in days, weeks, or months

    oai_token-act-pair · gpt-3.5-turbo

    units of time, such as days and weeks

    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
    rencies
    -0.64
     Thumbnails
    -0.64
    Images
    -0.63
     trillions
    -0.62
    ources
    -0.61
    ading
    -0.61
     Rooms
    -0.61
     Signs
    -0.61
     fabrics
    -0.61
     incor
    -0.60
    POSITIVE LOGITS
     stint
    1.06
     ordeal
    1.01
     period
    0.99
     hiatus
    0.97
     span
    0.94
     moratorium
    0.94
     stretch
    0.91
     affair
    0.89
     gap
    0.88
     delay
    0.87
    Activations Density 0.062%

    No Known Activations