© 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. 17163
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
    comed
    -0.73
     cascade
    -0.72
    coming
    -0.70
    levels
    -0.64
    ths
    -0.63
     ip
    -0.62
    cv
    -0.62
    tie
    -0.62
     downgrade
    -0.61
    cup
    -0.60
    POSITIVE LOGITS
     Dent
    0.91
    ĸļ
    0.77
    ouf
    0.74
     Vend
    0.70
    ovie
    0.70
    Sales
    0.68
     merch
    0.68
     Huffington
    0.67
    emis
    0.67
     Publishers
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.