© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3497
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passing of time or the end of a period

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time or approaching conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IPM
    -0.66
     Cosponsors
    -0.66
     AMA
    -0.63
     rebell
    -0.61
    zech
    -0.60
     Dalai
    -0.59
     dissent
    -0.57
     Indones
    -0.57
    istine
    -0.56
    ItemThumbnailImage
    -0.56
    POSITIVE LOGITS
     underway
    1.25
     OVER
    1.21
     over
    1.18
     nearing
    1.16
     winding
    1.08
     approaching
    0.97
     ending
    0.95
     upon
    0.92
     concluded
    0.91
     coming
    0.90
    Activations Density 0.201%

    No Known Activations