© 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. 11-RES-JB
    11. 17431
    Prev
    Next
    INDEX
    Explanations

    phrases related to continuity and ongoing actions over time

    oai_token-act-pair · gpt-3.5-turbo

    recurring themes of continuity and persistence over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Summary
    -0.58
    iuses
    -0.57
    omez
    -0.56
    loss
    -0.55
    urrencies
    -0.54
    ullivan
    -0.53
    etsk
    -0.53
    assin
    -0.53
     Lack
    -0.52
     simplicity
    -0.51
    POSITIVE LOGITS
     thereafter
    1.27
     until
    0.92
     hereafter
    0.90
     till
    0.90
     afterward
    0.83
     continue
    0.83
     afterwards
    0.81
     continuing
    0.81
     renewed
    0.80
     continued
    0.77
    Activations Density 0.313%

    No Known Activations