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. 11-RES-JB
    6. 22899
    Prev
    Next
    INDEX
    Explanations

    dates and event details

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oun
    -0.97
     metic
    -0.97
     smugglers
    -0.93
     eleph
    -0.90
     tyrann
    -0.90
     outweigh
    -0.87
     citiz
    -0.85
     prolifer
    -0.84
     spitting
    -0.84
     spir
    -0.84
    POSITIVE LOGITS
    Includes
    1.73
    October
    1.67
    Date
    1.66
    February
    1.65
    September
    1.65
    November
    1.64
    January
    1.63
    December
    1.62
    Address
    1.61
    July
    1.61
    Activations Density 0.240%

    No Known Activations