Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 17130
    Prev
    Next
    INDEX
    Explanations

    phrases related to the financial success or performance of movies, particularly focusing on box office figures

    oai_token-act-pair · gpt-3.5-turbo

    references to box office performance and related terms

    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
    pod
    -0.74
    ndra
    -0.70
     Labrador
    -0.68
    onomous
    -0.63
     Hast
    -0.62
     Pod
    -0.62
    lis
    -0.62
    Beg
    -0.60
    TON
    -0.60
     Lerner
    -0.59
    POSITIVE LOGITS
     receipts
    0.85
    eers
    0.79
     theaters
    0.77
    ovies
    0.73
     thriller
    0.71
     projections
    0.71
    ctors
    0.70
    buster
    0.70
    ographer
    0.68
     figures
    0.67
    Activations Density 0.033%

    No Known Activations