© 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. 20486
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    bass
    -0.67
    Balt
    -0.65
    inished
    -0.64
    ãĥ£
    -0.63
    Nor
    -0.63
    Pur
    -0.62
    pite
    -0.61
    bows
    -0.60
    parts
    -0.58
    ters
    -0.57
    POSITIVE LOGITS
     Allaah
    0.81
     Mandela
    0.81
     Rowling
    0.76
    croft
    0.75
     Ivanka
    0.75
     Isis
    0.73
     Canaver
    0.73
     Ney
    0.71
     Manziel
    0.71
     Christensen
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.