© 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. 8-RES-JB
    11. 20506
    Prev
    Next
    INDEX
    Explanations

    words related to time, specifically emphasizing earliness

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time references or temporal conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ales
    -0.72
    onsense
    -0.70
    leneck
    -0.70
    Reviewer
    -0.70
    sers
    -0.68
    ives
    -0.67
    eries
    -0.67
    alls
    -0.67
    rouse
    -0.67
    itivity
    -0.66
    POSITIVE LOGITS
     possible
    0.98
     practicable
    0.90
     Possible
    0.81
     2024
    0.72
     December
    0.70
     2030
    0.69
     2025
    0.68
     1955
    0.67
     June
    0.66
     September
    0.66
    Activations Density 0.037%

    No Known Activations