© 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. 12847
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a long duration or progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing duration or progress over 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
    selves
    -0.75
    ques
    -0.68
    amera
    -0.67
     Ambro
    -0.66
     squares
    -0.64
    MpServer
    -0.64
    oppers
    -0.63
    arnaev
    -0.63
    onom
    -0.62
    ackets
    -0.62
    POSITIVE LOGITS
     overdue
    1.08
    wind
    0.95
     way
    0.91
    shot
    0.90
    itudinal
    0.87
     ways
    0.87
     journey
    0.87
     awaited
    0.87
     road
    0.85
     slog
    0.84
    Activations Density 0.061%

    No Known Activations