© 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. 4-RES-JB
    11. 10709
    Prev
    Next
    INDEX
    Explanations

    names, particularly the name "Mike" with varying levels of importance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Mike."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ought
    -0.90
    istics
    -0.84
    itect
    -0.78
    arget
    -0.76
    uated
    -0.75
    sylvania
    -0.73
     lith
    -0.73
    uates
    -0.69
    icity
    -0.68
    hower
    -0.68
    POSITIVE LOGITS
     Tyson
    0.99
     Antonio
    0.88
     Trout
    0.83
     Brown
    0.82
     Adams
    0.81
     Daniels
    0.78
     Allen
    0.77
     Vick
    0.76
     Anderson
    0.76
     Rogers
    0.76
    Activations Density 0.006%

    No Known Activations