© 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. 2-RES-JB
    11. 17466
    Prev
    Next
    INDEX
    Explanations

    dates and time durations

    oai_token-act-pair · gpt-3.5-turbo

    references to time, specifically focusing on the concept of "last" as in preceding periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cil
    -0.70
    kaya
    -0.68
    /#
    -0.68
    rend
    -0.63
     Franch
    -0.62
    aunders
    -0.62
    stadt
    -0.62
    mbuds
    -0.61
    aband
    -0.61
    keyes
    -0.61
    POSITIVE LOGITS
     gasp
    0.97
     week
    0.94
     month
    0.93
     ditch
    0.92
     year
    0.91
     decade
    0.88
    ebin
    0.86
     night
    0.83
     Gleaming
    0.83
     rites
    0.79
    Activations Density 0.075%

    No Known Activations