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. 11-RES-JB
    6. 8810
    Prev
    Next
    INDEX
    Explanations

    verbs related to the concept of time, particularly focusing on the duration of actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of time and duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     agre
    -0.74
    lique
    -0.73
    vier
    -0.69
    mast
    -0.64
    ãĤ¦ãĤ¹
    -0.64
    ãĥĩãĤ£
    -0.63
    enture
    -0.63
    bda
    -0.62
    ateg
    -0.62
    redits
    -0.62
    POSITIVE LOGITS
     us
    0.94
     to
    0.86
     him
    0.82
     me
    0.78
     before
    0.73
    ume
    0.72
     for
    0.66
     them
    0.64
     Us
    0.61
     McDonnell
    0.61
    Activations Density 0.060%

    No Known Activations