© 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. 7-RES-JB
    11. 14293
    Prev
    Next
    INDEX
    Explanations

    specific modes of transportation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transportation methods, particularly air travel and subways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ²¾
    -0.96
    eful
    -0.94
    ificial
    -0.91
    kus
    -0.91
    lege
    -0.88
    erent
    -0.88
    terness
    -0.87
    ful
    -0.87
    bah
    -0.86
    icial
    -0.85
    POSITIVE LOGITS
     clutch
    0.76
     racks
    0.73
     swipe
    0.72
     shuffle
    0.68
     cradle
    0.67
     iPod
    0.66
     rack
    0.65
     slump
    0.65
     nucleus
    0.65
     analogy
    0.64
    Activations Density 0.091%

    No Known Activations