Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18743
    Prev
    Next
    INDEX
    Explanations

    strings that start with "to do."

    oai_token-act-pair · gpt-3.5-turbo

    contexts involving the concept of "doing" or performing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lights
    -0.72
    ussen
    -0.70
    pa
    -0.64
     Dispatch
    -0.64
    dayName
    -0.64
    mares
    -0.64
    Tai
    -0.63
    mare
    -0.63
    apego
    -0.63
    wagen
    -0.62
    POSITIVE LOGITS
    omsday
    0.99
    pez
    0.99
    omething
    0.93
    ozy
    0.88
    lez
    0.87
    oms
    0.84
    ppel
    0.82
    le
    0.78
    herty
    0.78
    oway
    0.77
    Activations Density 0.127%

    No Known Activations