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. 610
    Prev
    Next
    INDEX
    Explanations

    references to the trading card game Magic: The Gathering

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Magic" and related concepts within a specific context

    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
    lishes
    -0.80
    romising
    -0.71
     unsub
    -0.70
    dated
    -0.68
     Fas
    -0.68
    hovah
    -0.67
     fu
    -0.65
    heres
    -0.65
    nee
    -0.63
    lying
    -0.63
    POSITIVE LOGITS
     Leap
    0.91
    adelphia
    0.81
    haus
    0.78
    pedia
    0.77
    waukee
    0.76
     Missile
    0.75
    Magic
    0.74
     Beans
    0.74
     Properties
    0.73
    ssh
    0.73
    Activations Density 0.017%

    No Known Activations