© 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. 10-RES-JB
    11. 19068
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, specifically words related to past, present, and future events

    oai_token-act-pair · gpt-3.5-turbo

    the word "now" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.86
    habi
    -0.79
    insula
    -0.76
    ò
    -0.75
    advertisement
    -0.74
    æ©
    -0.72
    ked
    -0.70
     teasp
    -0.70
    drawn
    -0.69
    rongh
    -0.69
    POSITIVE LOGITS
     we
    1.17
     everybody
    1.03
     they
    1.02
    adays
    1.00
     you
    0.98
     it
    0.97
     everyone
    0.94
     somebody
    0.93
     I
    0.91
     everything
    0.87
    Activations Density 0.113%

    No Known Activations