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. 15418
    Prev
    Next
    INDEX
    Explanations

    temporal references such as days, weeks, months, and years, often indicating a specific duration since an event

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases related to the passage of 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
     appl
    -0.67
     Mechdragon
    -0.65
    rone
    -0.64
    inav
    -0.63
    alia
    -0.63
    alian
    -0.63
    ictive
    -0.61
     retrie
    -0.60
    ymes
    -0.59
    ibrary
    -0.58
    POSITIVE LOGITS
     preceding
    1.24
     leading
    0.99
     ahead
    0.94
     surrounding
    0.92
     following
    0.91
     ensuing
    0.89
     since
    0.87
     prior
    0.83
     beforehand
    0.83
     between
    0.82
    Activations Density 0.104%

    No Known Activations