© 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. 8-RES-JB
    11. 11399
    Prev
    Next
    INDEX
    Explanations

    text related to technical specifications and abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to technical or medical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flies
    -0.85
    taboola
    -0.72
    rir
    -0.72
    api
    -0.69
    vim
    -0.69
    avia
    -0.68
    bern
    -0.68
    want
    -0.67
     showc
    -0.67
    ç
    -0.66
    POSITIVE LOGITS
    Ds
    0.90
    Vs
    0.86
    Gs
    0.79
    Fs
    0.77
    vantage
    0.77
    dit
    0.75
    Ms
    0.75
     holders
    0.72
    FU
    0.71
    Ns
    0.70
    Activations Density 0.183%

    No Known Activations