© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13322
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific individual, likely "Bush"

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of a specific name or term associated with a person or concept

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     mate
    -0.64
     Galileo
    -0.63
     clipping
    -0.63
     worse
    -0.62
     diabetes
    -0.61
     cig
    -0.60
     Skinner
    -0.59
     Columb
    -0.59
     adultery
    -0.57
     carb
    -0.57
    POSITIVE LOGITS
    ush
    4.36
    USH
    1.94
    ushes
    1.92
    usha
    1.86
    usher
    1.65
    ushed
    1.60
    ushing
    1.46
    usk
    1.10
    ava
    1.10
    osh
    1.09
    Activations Density 0.008%

    No Known Activations