© 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. 0-RES-JB
    11. 18055
    Prev
    Next
    INDEX
    Explanations

    references to male individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "guy" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    held
    -0.65
    united
    -0.63
    amber
    -0.62
    flows
    -0.62
    empt
    -0.62
    ilies
    -0.62
     exceeding
    -0.61
    antine
    -0.61
     including
    -0.61
     Chapters
    -0.60
    POSITIVE LOGITS
     guy
    3.53
     dude
    2.65
     guys
    2.40
    guy
    2.28
     dudes
    2.07
     kid
    1.86
     Guys
    1.65
     Dude
    1.56
     man
    1.54
    Guy
    1.53
    Activations Density 0.017%

    No Known Activations