© 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. 7-RES-JB
    11. 7304
    Prev
    Next
    INDEX
    Explanations

    information related to product releases and technological developments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wrong
    -0.80
     Tears
    -0.71
     congr
    -0.65
    licks
    -0.65
     congratulations
    -0.65
     tragedies
    -0.65
    checking
    -0.63
     fallacy
    -0.62
     Wolves
    -0.62
    sorry
    -0.61
    POSITIVE LOGITS
     fitted
    0.92
     phased
    0.92
     housed
    0.92
     operated
    0.89
     redesigned
    0.88
    fitted
    0.87
     equipped
    0.85
     undergo
    0.85
     modeled
    0.82
     upgr
    0.82
    Activations Density 0.394%

    No Known Activations