© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14147
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations of companies, products, or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific brands, companies, or entities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    lain
    -0.66
    pection
    -0.62
    theless
    -0.62
    ĺħ
    -0.61
     cider
    -0.61
     continents
    -0.61
     sick
    -0.57
     arts
    -0.56
    iewicz
    -0.56
    hold
    -0.55
    POSITIVE LOGITS
    onomy
    0.98
    uple
    0.94
    uesday
    0.93
    olkien
    0.89
    onga
    0.87
    ribute
    0.86
    urtle
    0.86
    ARGET
    0.84
    olerance
    0.83
    itled
    0.83
    Activations Density 0.257%

    No Known Activations