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. 20078
    Prev
    Next
    INDEX
    Explanations

    keywords related to traffic and driving

    oai_token-act-pair · gpt-3.5-turbo

    topics related to traffic and driving violations

    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
     Flavoring
    -0.91
    aceutical
    -0.90
    sonian
    -0.89
    DragonMagazine
    -0.77
    olith
    -0.72
    rawdownloadcloneembedreportprint
    -0.72
    ilogy
    -0.71
    aspberry
    -0.71
    quartered
    -0.71
    ertain
    -0.71
    POSITIVE LOGITS
     motorists
    1.14
     traffic
    1.03
     bicycl
    1.00
     Traffic
    0.98
     Interstate
    0.96
     parked
    0.95
     drivers
    0.94
     Highway
    0.94
     err
    0.92
     lanes
    0.90
    Activations Density 0.154%

    No Known Activations