© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10289
    Prev
    Next
    INDEX
    Explanations

    time-related expressions like "year," "month," "decade," and "week."

    oai_token-act-pair · gpt-3.5-turbo

    references to time intervals and durations, specifically years and months

    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
    ystem
    -0.63
    uits
    -0.59
    omething
    -0.58
    '>
    -0.57
     gal
    -0.57
    hett
    -0.57
     constitu
    -0.57
    estine
    -0.56
     Pv
    -0.56
     Lans
    -0.56
    POSITIVE LOGITS
    long
    1.26
    ning
    1.07
    glass
    1.03
    's
    0.99
     ago
    0.89
    gap
    0.89
    wise
    0.88
    nen
    0.88
    iversary
    0.86
    shire
    0.83
    Activations Density 0.088%

    No Known Activations