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. 5616
    Prev
    Next
    INDEX
    Explanations

    the phrase "by the way"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the expression "by the way."

    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
    ĸļ
    -0.83
    incinn
    -0.77
    ¥ŀ
    -0.73
    uster
    -0.72
     nurs
    -0.70
    anmar
    -0.70
     corrid
    -0.68
     tremend
    -0.68
    usters
    -0.67
    ifer
    -0.65
    POSITIVE LOGITS
    ward
    0.82
    WARD
    0.74
    sey
    0.71
    fare
    0.70
    points
    0.68
    point
    0.67
    Bonus
    0.67
    chery
    0.66
    KEY
    0.65
     Pyth
    0.65
    Activations Density 0.013%

    No Known Activations