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. 7-RES-JB
    6. 638
    Prev
    Next
    INDEX
    Explanations

    sports-related events or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports outcomes, particularly wins and losses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Journals
    -0.82
    details
    -0.81
    ecd
    -0.80
     curric
    -0.72
    Filename
    -0.71
    cul
    -0.70
     concess
    -0.68
    rouch
    -0.67
    pmwiki
    -0.66
    chrome
    -0.65
    POSITIVE LOGITS
    wich
    0.85
     opener
    0.85
     Tulsa
    0.84
     snapped
    0.80
     Bye
    0.78
     Sunday
    0.77
     Saturday
    0.76
     Denver
    0.76
     Miami
    0.76
     Seattle
    0.76
    Activations Density 0.066%

    No Known Activations