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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 22919
    Prev
    Next
    INDEX
    Explanations

    references to awards for various achievements in sports and related fields

    oai_token-act-pair · gpt-3.5-turbo

    references to awards given in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INO
    -0.70
    arya
    -0.66
    aird
    -0.66
     dele
    -0.64
     oneself
    -0.64
    annis
    -0.62
    edly
    -0.61
    iosity
    -0.61
     itself
    -0.61
     alas
    -0.61
    POSITIVE LOGITS
     Month
    1.70
     Year
    1.51
     Week
    1.44
    Month
    1.36
     week
    1.27
     month
    1.26
     Century
    1.23
     year
    1.20
    week
    1.20
     YEAR
    1.18
    Activations Density 0.038%

    No Known Activations