© 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. 20510
    Prev
    Next
    INDEX
    Explanations

    the name "Martinez."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Martinez."

    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
    umbn
    -0.96
    pir
    -0.85
    umption
    -0.79
    ramid
    -0.77
    UTH
    -0.75
    ommel
    -0.75
    rha
    -0.73
    apter
    -0.71
    adder
    -0.71
    iblings
    -0.71
    POSITIVE LOGITS
     Martinez
    1.53
    inez
    1.23
     Alonso
    0.95
     Gonzalez
    0.90
     Ortiz
    0.87
     Gomez
    0.86
     Chavez
    0.84
    ards
    0.78
     Flores
    0.78
     Morales
    0.74
    Activations Density 0.010%

    No Known Activations