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. 21419
    Prev
    Next
    INDEX
    Explanations

    terms related to motorsports and car racing

    oai_token-act-pair · gpt-3.5-turbo

    references to the IndyCar racing series and related events

    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
    hillary
    -0.91
    byn
    -0.86
    ston
    -0.78
    cair
    -0.74
    child
    -0.71
    uman
    -0.71
    ndra
    -0.70
    asio
    -0.70
     Palin
    -0.68
    hoe
    -0.68
    POSITIVE LOGITS
     Playoffs
    1.10
     Champions
    1.02
     playoffs
    0.98
     Playoff
    0.97
     Championship
    0.96
    League
    0.91
     leagues
    0.87
     championships
    0.87
     Championships
    0.87
     Tournament
    0.86
    Activations Density 0.111%

    No Known Activations