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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 8246
    Prev
    Next
    INDEX
    Explanations

    incorrect statements or inaccuracies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     savvy
    -0.67
    ĸļ
    -0.66
    ocrat
    -0.65
    spoken
    -0.65
    ispers
    -0.65
    yssey
    -0.64
    sit
    -0.64
     fiercely
    -0.62
    oried
    -0.61
    entimes
    -0.60
    POSITIVE LOGITS
     "...
    0.92
     "âĢ¦
    0.82
     "(
    0.76
     exclude
    0.76
     \"
    0.74
     "+
    0.74
     \(
    0.74
     "[
    0.74
     "$
    0.73
     $\
    0.69
    Activations Density 0.724%

    No Known Activations