© 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. 0-RES-JB
    11. 11297
    Prev
    Next
    INDEX
    Explanations

    words related to timing

    oai_token-act-pair · gpt-3.5-turbo

    references to timing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leviathan
    -0.72
    Joined
    -0.70
    grown
    -0.67
    ylum
    -0.67
     Murd
    -0.65
    Ïģ
    -0.62
    ÃŃs
    -0.62
    NF
    -0.61
    aints
    -0.60
    borg
    -0.60
    POSITIVE LOGITS
     timing
    3.78
     timed
    1.75
    tim
    1.57
     tim
    1.39
     positioning
    1.36
     timeline
    1.33
     scheduling
    1.31
     coincidence
    1.29
     timetable
    1.28
     spacing
    1.28
    Activations Density 0.008%

    No Known Activations