© 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. 20503
    Prev
    Next
    INDEX
    Explanations

    terms related to medical instruments and certain foods, particularly mozzarella

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pendulums and their movements

    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
    mine
    -0.68
    riad
    -0.67
    ve
    -0.67
    nee
    -0.66
    riot
    -0.65
    ivity
    -0.64
    ¿
    -0.64
     Cosponsors
    -0.63
    ently
    -0.62
    ĨĴ
    -0.62
    POSITIVE LOGITS
    ulum
    1.51
    axis
    0.93
    veyard
    0.86
    issors
    0.83
    othal
    0.76
    uchi
    0.74
    $$$$
    0.72
    mania
    0.71
    oad
    0.70
    utherford
    0.69
    Activations Density 0.020%

    No Known Activations