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. 8-RES-JB
    6. 16063
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Before you" followed by an action or statement

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "before you" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.80
    Offline
    -0.72
    Wiki
    -0.64
     Consortium
    -0.63
    eret
    -0.63
     outnumbered
    -0.61
    natureconservancy
    -0.60
     Mafia
    -0.60
    ãĤ´
    -0.60
     Judd
    -0.59
    POSITIVE LOGITS
     embark
    1.02
     proceed
    0.93
    ope
    0.77
     begin
    0.76
    xit
    0.76
     succ
    0.75
     expires
    0.74
     expire
    0.72
     commence
    0.72
     succumb
    0.71
    Activations Density 0.082%

    No Known Activations