© 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. 12889
    Prev
    Next
    INDEX
    Explanations

    phrases containing the preposition "of."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a specific grouping or classification of items or people

    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
    ogly
    -0.67
    ovember
    -0.62
    verages
    -0.61
    uden
    -0.60
    gow
    -0.57
    pad
    -0.57
    KK
    -0.57
    uala
    -0.56
    ablishment
    -0.56
    afia
    -0.55
    POSITIVE LOGITS
     whom
    1.17
     which
    1.02
    which
    0.92
    whose
    0.78
     whence
    0.74
     whose
    0.73
     Which
    0.73
    nown
    0.71
    ãĥ´
    0.70
     theirs
    0.70
    Activations Density 0.131%

    No Known Activations