© 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. 2-RES-JB
    11. 9048
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chool
    -0.75
    FML
    -0.70
    clinton
    -0.70
    wal
    -0.69
    ¬¼
    -0.68
    org
    -0.67
    ugi
    -0.67
    Org
    -0.67
    tn
    -0.67
    inventoryQuantity
    -0.66
    POSITIVE LOGITS
    itives
    0.74
     Canad
    0.74
     Doctrine
    0.72
     Atmosp
    0.72
     Freed
    0.70
     Mankind
    0.68
     Pipeline
    0.67
     inquire
    0.67
     McKenna
    0.65
     notwithstanding
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.