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

    Neuronpedia

    Jacobian LensNEW
    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. 13672
    Prev
    Next
    INDEX
    Explanations

    the word "run" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "run."

    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
    illus
    -0.81
     Letters
    -0.72
    atti
    -0.68
    agher
    -0.66
    utics
    -0.66
     Factors
    -0.66
    Letter
    -0.64
    hib
    -0.63
    letters
    -0.63
    atto
    -0.63
    POSITIVE LOGITS
     run
    3.58
    run
    2.42
     runs
    2.31
     Run
    2.21
    Run
    2.14
     ran
    2.03
     RUN
    1.94
     Runs
    1.87
    runs
    1.84
     running
    1.82
    Activations Density 0.025%

    No Known Activations