© 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. 12-RES-JB
    11. 2399
    Prev
    Next
    INDEX
    Explanations

    keywords related to research methods and findings, scientific studies, and numerical values such as statistics

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    terms related to a variety of options or quantities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    escription
    -0.95
    atever
    -0.93
    isSpecial
    -0.92
    vertisement
    -0.91
    ò
    -0.87
    À
    -0.85
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.85
    ThumbnailImage
    -0.85
    ÿ
    -0.85
    Ě
    -0.85
    POSITIVE LOGITS
     of
    0.77
     topics
    0.52
     ranging
    0.52
     portfolios
    0.51
     variety
    0.49
     protocols
    0.49
     variables
    0.48
     undisclosed
    0.48
     dozen
    0.48
     pieces
    0.48
    Activations Density 0.046%

    No Known Activations