© 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. 16946
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating a higher degree or intensity of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that highlight comparisons or diminishing statements

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.77
    EMENT
    -0.69
    iona
    -0.69
     wipes
    -0.68
    Winged
    -0.68
     Juda
    -0.64
    alore
    -0.64
     havoc
    -0.62
     escal
    -0.60
     antit
    -0.60
    POSITIVE LOGITS
     nor
    0.73
     anything
    0.69
    astics
    0.67
    atos
    0.65
     satisfactory
    0.64
     anywhere
    0.63
     usual
    0.62
    mbuds
    0.61
     adequate
    0.61
     simply
    0.60
    Activations Density 0.074%

    No Known Activations