© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12791
    Prev
    Next
    INDEX
    Explanations

    specific time indicators, particularly past events

    oai_token-act-pair · gpt-3.5-turbo

    temporal expressions indicating the passage of time

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    arching
    -0.68
    seeking
    -0.65
    udeb
    -0.65
    selection
    -0.64
    SourceFile
    -0.63
    ranged
    -0.62
    718
    -0.61
    stration
    -0.61
    ongyang
    -0.61
    ãĥĺ
    -0.58
    POSITIVE LOGITS
    ,
    0.90
    adays
    0.83
     we
    0.80
     there
    0.75
    ,...
    0.66
     I
    0.65
     someone
    0.64
     today
    0.64
     nowadays
    0.62
    !,
    0.62
    Activations Density 0.164%

    No Known Activations