© 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. 4-RES-JB
    11. 17093
    Prev
    Next
    INDEX
    Explanations

    dates and times written in different formats

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "on" and similar prepositions

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

    No Comments

    Negative Logits
     rushing
    -0.62
     Tsukuyomi
    -0.61
     intervening
    -0.57
     Fib
    -0.55
     Roses
    -0.55
     Reynolds
    -0.55
     dial
    -0.54
     Cran
    -0.54
     Viz
    -0.53
     clinically
    -0.53
    POSITIVE LOGITS
    mast
    0.81
    merce
    0.75
    uff
    0.73
    livion
    0.73
    idate
    0.73
    cott
    0.72
    20439
    0.70
    oustic
    0.70
    ulate
    0.70
    arette
    0.69
    Activations Density 0.048%

    No Known Activations