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. 8-RES-JB
    6. 12717
    Prev
    Next
    INDEX
    Explanations

    time intervals, especially those related to future events

    oai_token-act-pair · gpt-3.5-turbo

    numerical references related to timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     envy
    -0.74
     scissors
    -0.64
     leveled
    -0.63
     mockery
    -0.62
    TextColor
    -0.61
     Telegram
    -0.58
     tender
    -0.58
    ogyn
    -0.57
     Selection
    -0.57
     turnout
    -0.56
    POSITIVE LOGITS
    mins
    0.97
    %.
    0.94
    th
    0.93
    km
    0.92
     milliseconds
    0.89
     mins
    0.88
     kilometres
    0.87
     years
    0.87
     minutes
    0.86
     kilometers
    0.83
    Activations Density 0.100%

    No Known Activations