© 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. 20547
    Prev
    Next
    INDEX
    Explanations

    Proper names related to an entity or individual named "Tr" followed by a varying number of characters, possibly part of a longer name or title

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the abbreviation "Tr" or related terms

    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
    furt
    -0.74
    ELS
    -0.73
     actionGroup
    -0.69
    eers
    -0.68
    MENTS
    -0.67
    foundland
    -0.65
    66666666
    -0.65
    BILITIES
    -0.65
     documented
    -0.64
    manship
    -0.63
    POSITIVE LOGITS
    izoph
    1.04
    istan
    1.02
    itton
    1.01
    ilateral
    0.97
    acer
    0.96
    unn
    0.94
    icol
    0.90
    asury
    0.90
    unks
    0.89
    unk
    0.88
    Activations Density 0.004%

    No Known Activations