Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10012
    Prev
    Next
    INDEX
    Explanations

    dates and timing-related information

    oai_token-act-pair · gpt-3.5-turbo

    specific time indicators, including months, years, and related phrases about timing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stranger
    -0.66
    edIn
    -0.63
    ographed
    -0.62
     lately
    -0.61
    Liter
    -0.61
     VIDEOS
    -0.59
     typed
    -0.59
    atem
    -0.58
     testim
    -0.58
     CTRL
    -0.58
    POSITIVE LOGITS
     2019
    1.25
     tomorrow
    1.24
     2021
    1.14
     2020
    0.99
    2019
    0.98
     next
    0.98
     2018
    0.96
     2025
    0.95
    morrow
    0.94
     2024
    0.92
    Activations Density 0.253%

    No Known Activations