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. 3497
    Prev
    Next
    INDEX
    Explanations

    phrases related to various types of systems, such as healthcare systems, school systems, immune systems, financial systems, and more

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of systems across different contexts

    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
    forth
    -0.78
    amen
    -0.67
    tein
    -0.67
    alloween
    -0.66
    zzy
    -0.66
    jew
    -0.66
    Hispanic
    -0.65
    inness
    -0.65
     Wife
    -0.64
    dress
    -0.63
    POSITIVE LOGITS
     systems
    3.59
     Systems
    2.62
     system
    2.41
     SYSTEM
    2.14
    system
    2.04
     System
    1.98
    System
    1.83
     subsystem
    1.64
     networks
    1.60
     machines
    1.56
    Activations Density 0.018%

    No Known Activations