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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 2406
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and acknowledgment towards specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    acknowledgments or expressions of gratitude

    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
    dom
    -0.73
    urations
    -0.72
    ieties
    -0.72
     expectancy
    -0.71
    window
    -0.71
    moil
    -0.69
    lock
    -0.69
    ESA
    -0.68
    ntil
    -0.68
    Gov
    -0.68
    POSITIVE LOGITS
     formatting
    0.94
     sponsoring
    0.93
     tip
    0.92
     spotting
    0.92
     translator
    0.90
     translations
    0.89
     Donation
    0.88
     invaluable
    0.88
     translation
    0.88
     transcription
    0.85
    Activations Density 0.180%

    No Known Activations