© 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. 12997
    Prev
    Next
    INDEX
    Explanations

    the letter "y" repeated multiple times consecutively

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'y' in various contexts

    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
     Wonderland
    -0.81
    ULAR
    -0.71
    Oracle
    -0.66
    IUM
    -0.65
     Sporting
    -0.65
     Staples
    -0.64
     Prelude
    -0.64
    ãĥ´ãĤ¡
    -0.64
     Excellence
    -0.63
     PowerPoint
    -0.62
    POSITIVE LOGITS
    ahoo
    1.17
    orkshire
    1.04
    ield
    1.02
    idd
    1.02
    ummy
    1.02
    olk
    1.01
    outh
    0.98
    anked
    0.98
    onder
    0.96
    aku
    0.93
    Activations Density 0.022%

    No Known Activations