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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 10833
    Prev
    Next
    INDEX
    Explanations

    phrases related to music and movies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific songs or musical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.80
     seiz
    -0.75
    Newsletter
    -0.69
    emouth
    -0.66
    yth
    -0.62
     guiActiveUn
    -0.62
     Practices
    -0.61
     staging
    -0.60
    annis
    -0.60
    Īè
    -0.59
    POSITIVE LOGITS
     Coyotes
    0.68
    iland
    0.64
     istg
    0.64
    azo
    0.62
    loo
    0.62
     IU
    0.62
    idine
    0.60
    âĢ¢âĢ¢
    0.59
     Kinnikuman
    0.59
     Rebels
    0.59
    Activations Density 0.283%

    No Known Activations