© 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. 1-RES-JB
    11. 3803
    Prev
    Next
    INDEX
    Explanations

    references to the word "Bus"

    oai_token-act-pair · gpt-3.5-turbo

    references to public transportation, specifically buses

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Pradesh
    -0.67
     Pharaoh
    -0.65
    ONY
    -0.65
    arily
    -0.65
     concerned
    -0.59
     cogn
    -0.59
    vironment
    -0.56
     Rodham
    -0.56
     emergence
    -0.56
     observation
    -0.56
    POSITIVE LOGITS
    loads
    1.11
    Bus
    1.00
    bus
    0.97
    dump
    0.97
    driver
    0.93
    load
    0.89
    hel
    0.89
     Bus
    0.83
    pipe
    0.82
    ility
    0.79
    Activations Density 0.012%

    No Known Activations