© 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. 7-RES-JB
    11. 24104
    Prev
    Next
    INDEX
    Explanations

    phrases related to time sequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases conveying the passage of time, particularly events occurring "later."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.80
    quartered
    -0.78
    ãĤ¢ãĥ«
    -0.74
    gow
    -0.73
    ãĥ´
    -0.72
    erver
    -0.70
     largeDownload
    -0.70
    ãĤ´
    -0.70
    scribe
    -0.68
    OW
    -0.67
    POSITIVE LOGITS
     however
    0.87
     when
    0.79
     confronted
    0.77
     alas
    0.71
     though
    0.66
     alerted
    0.66
    when
    0.64
     Mehran
    0.64
     exhausted
    0.64
     although
    0.63
    Activations Density 0.204%

    No Known Activations