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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 3226
    Prev
    Next
    INDEX
    Explanations

    mentions of playing cards in the context of games or competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to gaming cards and their mechanics

    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
    ¿½
    -0.74
    ItemTracker
    -0.72
    Īè
    -0.71
    heric
    -0.71
    ationally
    -0.71
    geoning
    -0.69
     Podesta
    -0.66
     earthqu
    -0.66
    ör
    -0.65
     NGO
    -0.65
    POSITIVE LOGITS
    inals
    1.07
     cards
    1.00
     sleeves
    0.96
    igan
    0.93
    igans
    0.91
    backs
    0.89
    iologist
    0.87
    cards
    0.86
     issu
    0.85
    ozo
    0.83
    Activations Density 0.017%

    No Known Activations