© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 768
    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
     heaviest
    -0.78
     ever
    -0.71
     displacement
    -0.65
     mean
    -0.64
     patronage
    -0.63
     brackets
    -0.63
     retention
    -0.63
     Cav
    -0.63
     ratios
    -0.62
     Pesh
    -0.62
    POSITIVE LOGITS
    itiz
    0.86
    heim
    0.83
    egu
    0.80
    \\\\
    0.77
    acial
    0.76
    ãĥ³
    0.74
    assetsadobe
    0.73
    WHERE
    0.73
    iery
    0.73
    utherford
    0.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.