© 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. 20490
    Prev
    Next
    INDEX
    Explanations

    instances of the word "if"

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that begin with "if."

    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
    Eye
    -0.79
    ãĤª
    -0.76
    Rated
    -0.75
    ãĤ¨ãĥ«
    -0.75
    FTWARE
    -0.72
    ORPG
    -0.68
    Materials
    -0.67
    %);
    -0.65
    emetery
    -0.63
    Poké
    -0.61
    POSITIVE LOGITS
    soever
    1.03
    fy
    0.98
    rame
    0.89
     you
    0.85
    yip
    0.82
     unchecked
    0.79
     they
    0.78
    etheless
    0.73
     anything
    0.73
    tar
    0.72
    Activations Density 0.091%

    No Known Activations