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. 0-RES-JB
    6. 21120
    Prev
    Next
    INDEX
    Explanations

    references to movie theaters in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "theater" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ework
    -0.73
    ijk
    -0.67
     Aad
    -0.66
    ainer
    -0.66
     labelled
    -0.62
     Straw
    -0.62
    erry
    -0.61
    ulator
    -0.61
     trait
    -0.61
     graft
    -0.60
    POSITIVE LOGITS
     theaters
    4.15
     theater
    2.55
     theat
    2.43
     Theater
    1.94
     theatre
    1.90
     cinem
    1.85
     screenings
    1.65
     cinema
    1.60
     movies
    1.48
     Theatre
    1.45
    Activations Density 0.019%

    No Known Activations