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. 10-RES-JB
    6. 9380
    Prev
    Next
    INDEX
    Explanations

    phrases related to time duration

    oai_token-act-pair · gpt-3.5-turbo

    references to duration or continuity in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artisan
    -0.62
    iform
    -0.54
     Cosponsors
    -0.53
    ocrats
    -0.49
    ohl
    -0.49
    ELL
    -0.48
    IRO
    -0.48
     Concern
    -0.47
     narrowly
    -0.47
     faces
    -0.46
    POSITIVE LOGITS
     thereof
    0.95
     of
    0.88
     eternity
    0.87
    idays
    0.84
    imester
    0.82
     duration
    0.80
     periods
    0.79
    week
    0.79
    nesday
    0.74
    urations
    0.73
    Activations Density 0.122%

    No Known Activations