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. 4656
    Prev
    Next
    INDEX
    Explanations

    phrases related to software or operations running or being executed

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "running on" followed by various contexts or systems

    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
    Bey
    -0.81
    zsche
    -0.75
    BUT
    -0.73
    ï¸ı
    -0.72
    lege
    -0.72
    URA
    -0.70
    bryce
    -0.70
    Cod
    -0.69
    $$
    -0.69
    BOOK
    -0.69
    POSITIVE LOGITS
     behalf
    1.39
     Sundays
    1.03
     weekends
    1.02
    etime
    0.94
     fumes
    0.90
     rooft
    0.87
     Saturdays
    0.87
    yx
    0.84
     occasion
    0.83
    site
    0.80
    Activations Density 0.185%

    No Known Activations