© 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. 17727
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passage of time

    oai_token-act-pair · gpt-3.5-turbo

    transitional phrases indicating the passage of time

    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
    SourceFile
    -0.86
    ãĤ´ãĥ³
    -0.82
    TA
    -0.79
    ãĥ¥
    -0.72
    apest
    -0.72
    scribe
    -0.70
    ãĥ´
    -0.68
    Cause
    -0.68
    ãĤ´
    -0.67
    quartered
    -0.66
    POSITIVE LOGITS
     however
    1.15
     somew
    1.09
     though
    0.91
     when
    0.84
     alas
    0.82
     whenever
    0.76
     although
    0.76
     sensing
    0.76
     realizing
    0.75
    upon
    0.75
    Activations Density 0.202%

    No Known Activations