© 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 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. 10-RES-JB
    11. 3494
    Prev
    Next
    INDEX
    Explanations

    numerical file size information in kilobytes (KB) and megabytes (MB)

    oai_token-act-pair · gpt-3.5-turbo

    metrics and specifications related to file sizes and data transfers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.75
     Tanner
    -0.70
    icut
    -0.68
    itiveness
    -0.66
     wealthier
    -0.65
     curfew
    -0.64
     Dion
    -0.63
     retribution
    -0.63
     lev
    -0.63
     ignited
    -0.63
    POSITIVE LOGITS
    KB
    1.53
    kb
    1.51
    MB
    1.49
     bytes
    1.38
    Gb
    1.38
    kB
    1.38
    abytes
    1.28
    bytes
    1.22
    GB
    1.21
    mb
    1.19
    Activations Density 0.169%

    No Known Activations