© 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. 1-RES-JB
    11. 10345
    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
    Not in Any Lists

    No Comments

    Negative Logits
    pread
    -0.71
    ilege
    -0.71
    trust
    -0.68
    igma
    -0.67
    WARD
    -0.64
    lot
    -0.64
     Tickets
    -0.64
    acebook
    -0.63
    www
    -0.63
    AAAAAAAA
    -0.61
    POSITIVE LOGITS
    milo
    0.73
     Appalachian
    0.65
    ymes
    0.65
    oglu
    0.63
    ï¸ı
    0.61
     [|
    0.61
    pects
    0.61
     elim
    0.60
    ItemTracker
    0.60
     Kyoto
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.