© 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. 20551
    Prev
    Next
    INDEX
    Explanations

    mentions of theaters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "theater."

    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
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
    arov
    -0.66
    eros
    -0.65
    Il
    -0.65
    TON
    -0.63
     DATA
    -0.62
    pages
    -0.61
    ODE
    -0.61
     concise
    -0.61
     recol
    -0.60
    POSITIVE LOGITS
     theater
    1.39
     theatre
    1.30
     Theater
    1.07
     theat
    1.05
     theaters
    1.04
    wright
    0.97
    goers
    0.92
     Royale
    0.84
    itone
    0.84
    isans
    0.78
    Activations Density 0.008%

    No Known Activations