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. 13806
    Prev
    Next
    INDEX
    Explanations

    titles of video games, especially those in the Final Fantasy series

    oai_token-act-pair · gpt-3.5-turbo

    mentions of video game titles, particularly in the fantasy genre

    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
    conserv
    -0.94
     clot
    -0.77
    aspberry
    -0.76
    uckland
    -0.75
    bnb
    -0.69
    ervation
    -0.68
     eleph
    -0.66
    selection
    -0.65
    prus
    -0.64
     neut
    -0.64
    POSITIVE LOGITS
     Generations
    0.94
     Characters
    0.85
     XIII
    0.85
     Tactics
    0.83
     Kingdom
    0.79
     0004
    0.79
     XIV
    0.78
     Portable
    0.77
     Fatal
    0.77
     Trilogy
    0.77
    Activations Density 0.057%

    No Known Activations