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. 11675
    Prev
    Next
    INDEX
    Explanations

    mentions of the video game "Destiny"

    oai_token-act-pair · gpt-3.5-turbo

    references to the video game "Destiny" and its associated elements

    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
    geries
    -0.81
    odynam
    -0.79
    icides
    -0.74
    sburgh
    -0.73
    esc
    -0.72
    enegger
    -0.72
    govtrack
    -0.71
    mediate
    -0.69
    ouf
    -0.67
    opted
    -0.67
    POSITIVE LOGITS
     Tracker
    0.86
     Destiny
    0.85
     Royale
    0.79
     Duty
    0.74
     Directorate
    0.71
    pedia
    0.69
    Bound
    0.67
     Frontier
    0.67
    cean
    0.66
     Bungie
    0.66
    Activations Density 0.036%

    No Known Activations