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. 0-RES-JB
    6. 9352
    Prev
    Next
    INDEX
    Explanations

    configuration settings or setups within text

    oai_token-act-pair · gpt-3.5-turbo

    references to technical setups or arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wolves
    -0.77
    nee
    -0.72
    ews
    -0.71
    rue
    -0.69
    aid
    -0.65
    fair
    -0.65
     Booker
    -0.65
     abs
    -0.65
    Kid
    -0.64
     âĸº
    -0.64
    POSITIVE LOGITS
     configuration
    3.38
     configurations
    2.81
     Configuration
    2.28
     config
    2.04
    Configuration
    2.04
     configured
    1.89
    Config
    1.82
    config
    1.79
     Config
    1.73
     configure
    1.72
    Activations Density 0.023%

    No Known Activations