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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 9178
    Prev
    Next
    INDEX
    Explanations

    time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    the word "shortly" in various contexts, indicating a focus on time-related transitions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lace
    -0.71
    ICAN
    -0.69
    elson
    -0.66
    lik
    -0.65
    ortium
    -0.65
    CHQ
    -0.63
    ajo
    -0.63
    beit
    -0.62
     Responsibility
    -0.62
    severe
    -0.61
    POSITIVE LOGITS
     thereafter
    1.28
    aneously
    0.91
    mares
    0.89
     afterward
    0.89
     afterwards
    0.88
    entimes
    0.80
    eteenth
    0.76
     followed
    0.76
    teenth
    0.76
     enough
    0.74
    Activations Density 0.020%

    No Known Activations