© 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. 13127
    Prev
    Next
    INDEX
    Explanations

    symbols and technical terms related to specific concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of special characters or symbols that may indicate specific formats or expressions

    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
    ysis
    -0.84
    iple
    -0.78
     redes
    -0.67
     parted
    -0.65
    ettel
    -0.65
     graz
    -0.64
    oller
    -0.63
     Borg
    -0.63
     redress
    -0.62
    ijn
    -0.62
    POSITIVE LOGITS
    20439
    0.97
    _>
    0.88
    女
    0.85
    advertisement
    0.83
    specific
    0.82
    craft
    0.82
    VALUE
    0.80
    double
    0.79
    advertising
    0.79
    leaning
    0.79
    Activations Density 0.041%

    No Known Activations