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

    Neuronpedia

    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. 8204
    Prev
    Next
    INDEX
    Explanations

    phrases related to railways

    oai_token-act-pair · gpt-3.5-turbo

    terms related to railways and railroad systems

    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
     moms
    -0.78
     Hera
    -0.75
     Alicia
    -0.75
     MVP
    -0.73
     Zack
    -0.71
    Mom
    -0.70
    Pal
    -0.69
     Vanessa
    -0.68
     mom
    -0.68
    esis
    -0.67
    POSITIVE LOGITS
     railway
    3.30
     Railway
    3.21
     railroad
    2.98
     railways
    2.85
     Railroad
    2.75
    Rail
    2.04
     rail
    1.99
     Rail
    1.80
     locom
    1.69
     Amtrak
    1.58
    Activations Density 0.013%

    No Known Activations