© 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. 4-RES-JB
    11. 963
    Prev
    Next
    INDEX
    Explanations

    words with contractions ending in "'t"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wouldn't."

    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
    Reviewer
    -0.80
     ventilation
    -0.73
    strength
    -0.69
     Vit
    -0.62
     compar
    -0.62
     Colour
    -0.61
     Gleaming
    -0.61
     Balkans
    -0.60
     comparative
    -0.59
     Radiation
    -0.59
    POSITIVE LOGITS
    urtle
    1.02
    acular
    0.88
    otally
    0.87
    ruck
    0.85
    weet
    0.84
    entimes
    0.83
    urtles
    0.83
    enegger
    0.82
    ouched
    0.82
     necessarily
    0.80
    Activations Density 0.037%

    No Known Activations