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. 6-RES-JB
    6. 18191
    Prev
    Next
    INDEX
    Explanations

    dates in specific formats

    oai_token-act-pair · gpt-3.5-turbo

    dates and timestamps in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    month-day-year dates, especially if preceded by the word "Following"

    date in 2017

    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accompanied
    -0.77
    soDeliveryDate
    -0.62
     Yad
    -0.61
    Dex
    -0.60
     pregn
    -0.59
     scapego
    -0.58
     foremost
    -0.58
    Poké
    -0.57
     spo
    -0.57
    anooga
    -0.56
    POSITIVE LOGITS
     Invalid
    0.75
     08
    0.73
    Invalid
    0.72
     07
    0.69
     09
    0.68
    iatus
    0.68
     [+]
    0.64
     Merge
    0.64
     06
    0.63
     05
    0.63
    Activations Density 0.129%

    No Known Activations