© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 10673
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oil
    -0.73
    liga
    -0.72
    iferation
    -0.71
    ================================================================
    -0.68
    itsch
    -0.68
     prosecutions
    -0.65
    buquerque
    -0.65
    ãĥĥãĥī
    -0.65
     Outbreak
    -0.65
    lua
    -0.64
    POSITIVE LOGITS
    DIT
    0.71
     Mechanical
    0.68
     mileage
    0.67
    arger
    0.66
     rebate
    0.65
     premium
    0.65
     vic
    0.62
     selective
    0.62
     hereafter
    0.60
     Caller
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.