© 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. 1-RES-JB
    11. 20535
    Prev
    Next
    INDEX
    Explanations

    the word "prop" alongside various suffixes and prefixes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific chemical compounds, particularly propylene and its derivatives

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Carbuncle
    -0.81
    ãĤ¼ãĤ¦ãĤ¹
    -0.71
     Cities
    -0.70
    edin
    -0.69
     Plain
    -0.69
    soever
    -0.68
    Interstitial
    -0.68
     Crossing
    -0.66
    Americans
    -0.65
    MORE
    -0.64
    POSITIVE LOGITS
     prop
    1.24
    itious
    1.00
    ulsive
    0.94
    hetically
    0.91
    onents
    0.87
    ylene
    0.85
    hetical
    0.84
    etry
    0.82
    hetics
    0.81
    etric
    0.81
    Activations Density 0.007%

    No Known Activations