© 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. 20529
    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
    ¶ħ
    -0.73
     bis
    -0.73
    avia
    -0.66
    esi
    -0.64
    book
    -0.63
    audi
    -0.63
     Leilan
    -0.63
     Anniversary
    -0.62
     Norn
    -0.62
     Rai
    -0.62
    POSITIVE LOGITS
    espie
    0.75
     tabl
    0.67
    olver
    0.66
     toget
    0.64
    ammers
    0.64
    multipl
    0.62
     Liver
    0.62
     Maver
    0.61
    urity
    0.61
    aghetti
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.