© 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. 1-RES-JB
    11. 20502
    Prev
    Next
    INDEX
    Explanations

    co-authors of studies or articles

    oai_token-act-pair · gpt-3.5-turbo

    references to co-authors in research or studies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Spears
    -0.74
     Leica
    -0.71
    EMS
    -0.71
     Poles
    -0.70
    tto
    -0.70
     Spa
    -0.69
     nylon
    -0.69
     valve
    -0.65
     Dortmund
    -0.65
     Cot
    -0.65
    POSITIVE LOGITS
    itatively
    1.33
    author
    1.17
    ournals
    1.13
    essee
    1.03
    lisher
    1.03
    itative
    1.02
    itarian
    0.96
    itors
    0.95
    lishing
    0.92
    creator
    0.92
    Activations Density 0.011%

    No Known Activations