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. 1-RES-JB
    6. 1468
    Prev
    Next
    INDEX
    Explanations

    sentences related to the creation of products, projects, or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "create" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phia
    -0.79
     Uz
    -0.62
    bes
    -0.62
     Mitt
    -0.61
     Mandatory
    -0.60
     McGr
    -0.59
     Buffett
    -0.58
    Wal
    -0.58
    ma
    -0.57
     Clin
    -0.56
    POSITIVE LOGITS
    resses
    0.93
    smanship
    0.87
    ãĥķãĤ¡
    0.86
    女
    0.84
    ãĥĩãĤ£
    0.83
    furt
    0.79
    ãĤ©
    0.77
    aldehyde
    0.76
    gallery
    0.75
    creat
    0.75
    Activations Density 0.031%

    No Known Activations