© 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. 8-RES-JB
    11. 14120
    Prev
    Next
    INDEX
    Explanations

    instances where contrasting statements are made

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "But" and various conjunctions indicating contrast or exception

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    gie
    -0.81
    lol
    -0.78
    Finish
    -0.75
    sword
    -0.73
    onica
    -0.69
    amus
    -0.69
    uminati
    -0.69
    ëĭ
    -0.69
    Woman
    -0.68
    girl
    -0.68
    POSITIVE LOGITS
     whereas
    0.95
    ccording
    0.95
     empirical
    0.94
     policymakers
    0.89
     anecdotal
    0.88
     proponents
    0.87
     researchers
    0.86
     there
    0.86
     economists
    0.85
     methodological
    0.85
    Activations Density 0.349%

    No Known Activations