© 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. 9122
    Prev
    Next
    INDEX
    Explanations

    time-related terms related to significant periods, such as decades and centuries

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations, specifically decades and centuries

    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
     pickups
    -0.65
     Alic
    -0.64
     Vinyl
    -0.58
     Gorge
    -0.58
     ãĢĮ
    -0.56
    iants
    -0.55
    :(
    -0.53
     HIP
    -0.53
     FM
    -0.52
     exceptions
    -0.52
    POSITIVE LOGITS
    long
    1.35
    old
    0.95
    '-
    0.90
    -
    0.84
     ago
    0.83
    worn
    0.83
    span
    0.82
    cffffcc
    0.78
    worth
    0.78
     of
    0.77
    Activations Density 0.098%

    No Known Activations