© 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. 17149
    Prev
    Next
    INDEX
    Explanations

    words related to spirituality or metaphysical concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Spirit" associated with different contexts and meanings

    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
     pse
    -0.71
    tics
    -0.65
    ften
    -0.62
    theless
    -0.61
     nightmares
    -0.61
     hereditary
    -0.60
     hatched
    -0.59
    skirts
    -0.59
    enegger
    -0.59
     sidel
    -0.59
    POSITIVE LOGITS
    uality
    1.56
    ually
    0.97
    ual
    0.93
    uous
    0.90
     Tracks
    0.85
     Spirit
    0.82
    Spirit
    0.81
    adelphia
    0.79
    atorium
    0.78
    tip
    0.76
    Activations Density 0.007%

    No Known Activations