© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11631
    Prev
    Next
    INDEX
    Explanations

    terms related to box office performance and financial success in the film industry

    oai_token-act-pair · gpt-3.5-turbo

    terms related to box office performance and financial statistics of films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flask
    -0.74
     Students
    -0.71
    onomous
    -0.68
     sshd
    -0.68
     Oss
    -0.67
     Pastebin
    -0.65
    laus
    -0.65
    sonian
    -0.65
    CHAT
    -0.63
     biom
    -0.63
    POSITIVE LOGITS
     debut
    0.99
     domestically
    0.94
     theaters
    0.89
     gross
    0.88
     darling
    0.85
     sequels
    0.83
     blockbuster
    0.83
     receipts
    0.80
    atinum
    0.80
    gross
    0.78
    Activations Density 0.086%

    No Known Activations