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. 21999
    Prev
    Next
    INDEX
    Explanations

    movie titles

    oai_token-act-pair · gpt-3.5-turbo

    titles and key phrases from popular entertainment franchises or series

    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
    imentary
    -0.78
    uckland
    -0.77
    prus
    -0.77
    ickr
    -0.75
    fed
    -0.74
    uga
    -0.73
     dispersed
    -0.72
     knowledgeable
    -0.71
    arij
    -0.70
     retire
    -0.69
    POSITIVE LOGITS
     sequels
    1.11
     Trilogy
    1.02
     trilogy
    1.01
     Animated
    0.99
     films
    0.98
     soundtrack
    0.97
     Seasons
    0.95
     sequel
    0.95
    Movie
    0.93
     Movie
    0.92
    Activations Density 0.179%

    No Known Activations