© 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. 0-RES-JB
    11. 13130
    Prev
    Next
    INDEX
    Explanations

    instances of the word "presentation" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "presentation" and its variants

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    leep
    -0.82
    ctuary
    -0.79
    ãģ®éŃĶ
    -0.69
    ousands
    -0.68
    addons
    -0.67
     forgive
    -0.66
     banned
    -0.65
     outlawed
    -0.65
     Cruel
    -0.65
     hurt
    -0.63
    POSITIVE LOGITS
     presentation
    3.77
     presentations
    2.91
     presenting
    1.88
     Present
    1.58
     keynote
    1.53
     PowerPoint
    1.48
    Present
    1.47
     slideshow
    1.43
     exposition
    1.40
     presenter
    1.38
    Activations Density 0.014%

    No Known Activations