© 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. 14344
    Prev
    Next
    INDEX
    Explanations

    references to different countries and industries

    oai_token-act-pair · gpt-3.5-turbo

    words related to various industries, countries, and locations

    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
    aughs
    -0.75
    ilogy
    -0.67
    DOS
    -0.67
    esome
    -0.65
    issance
    -0.62
    enegger
    -0.61
    esi
    -0.60
     Pione
    -0.59
    iffe
    -0.59
    ieu
    -0.58
    POSITIVE LOGITS
     ranging
    1.10
    afety
    0.88
     like
    0.87
     unrelated
    0.85
     resembling
    0.82
     LIKE
    0.81
     outside
    0.80
     deemed
    0.80
    cience
    0.76
     beyond
    0.76
    Activations Density 0.381%

    No Known Activations