© 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. 3-RES-JB
    11. 17245
    Prev
    Next
    INDEX
    Explanations

    phrases related to time durations

    oai_token-act-pair · gpt-3.5-turbo

    time-related expressions and durations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    SourceFile
    -0.76
    ById
    -0.74
     Cosponsors
    -0.71
    advertisement
    -0.69
    Platform
    -0.66
     Mechdragon
    -0.66
    tainment
    -0.64
    Planet
    -0.63
    lihood
    -0.62
     buttons
    -0.62
    POSITIVE LOGITS
     devoted
    0.79
    depending
    0.74
    isode
    0.70
     culminating
    0.69
     adolesc
    0.69
    iversary
    0.68
    culated
    0.67
     onwards
    0.67
     spent
    0.66
     accumulated
    0.64
    Activations Density 1.359%

    No Known Activations