© 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. 8-RES-JB
    11. 13035
    Prev
    Next
    INDEX
    Explanations

    phrases related to public events or gatherings

    oai_token-act-pair · gpt-3.5-turbo

    sentences indicating the presence of gatherings or collective activities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     inherited
    -0.91
     extinct
    -0.87
     ageing
    -0.86
     obsolete
    -0.85
     immortality
    -0.83
     inheritance
    -0.82
     reck
    -0.80
     biological
    -0.78
     dependency
    -0.78
     defaults
    -0.78
    POSITIVE LOGITS
     Participants
    1.23
     Attend
    1.20
     Protesters
    1.16
     Afterwards
    1.15
     Dozens
    1.13
     Guests
    1.13
    Fans
    1.10
    Particip
    1.08
     Visitors
    1.07
    Members
    1.06
    Activations Density 0.666%

    No Known Activations