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. 8-RES-JB
    6. 271
    Prev
    Next
    INDEX
    Explanations

    mentions of the celebrity name "Britney" and variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    references to British celebrities or cultural elements, particularly focusing on their names or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.76
     recess
    -0.71
    ATING
    -0.71
    CVE
    -0.70
    Topics
    -0.70
    externalActionCode
    -0.67
    ATIVE
    -0.67
    orse
    -0.65
    ATA
    -0.65
     1886
    -0.64
    POSITIVE LOGITS
    ney
    1.03
    ishers
    1.00
    pop
    0.92
     Spears
    0.91
    ician
    0.91
    oons
    0.87
     Hume
    0.87
    tex
    0.87
    ches
    0.87
    odi
    0.85
    Activations Density 0.050%

    No Known Activations