© 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. 7141
    Prev
    Next
    INDEX
    Explanations

    phrases related to timelines

    oai_token-act-pair · gpt-3.5-turbo

    references to timelines or chronological sequences of events

    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
    amiya
    -0.79
    ãģį
    -0.79
    unin
    -0.78
    ateurs
    -0.74
    iasis
    -0.73
    otto
    -0.73
    ãĥīãĥ©
    -0.73
    ateur
    -0.72
    bery
    -0.72
    Interstitial
    -0.71
    POSITIVE LOGITS
     timelines
    1.08
     timeline
    1.06
     elapsed
    0.94
     timeframe
    0.90
     Timeline
    0.89
     timetable
    0.83
     Clock
    0.82
    cale
    0.79
     continuum
    0.78
     Chron
    0.75
    Activations Density 0.057%

    No Known Activations