© 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. 3-RES-JB
    11. 17004
    Prev
    Next
    INDEX
    Explanations

    phrases related to fictional titles and sequels

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Infinity" and "Eternity" themes in movies or media

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ages
    -0.72
    ebin
    -0.70
    edy
    -0.69
    EF
    -0.68
    âķIJâķIJ
    -0.68
    nick
    -0.68
    д
    -0.67
    mit
    -0.66
    edo
    -0.66
     convincing
    -0.65
    POSITIVE LOGITS
     Infinity
    0.94
     Gauntlet
    0.90
     Stones
    0.82
    inite
    0.74
    aucus
    0.73
    ãĤ¼ãĤ¦ãĤ¹
    0.71
    cean
    0.70
    iculture
    0.70
    halla
    0.69
     Runes
    0.68
    Activations Density 0.018%

    No Known Activations