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. 10-RES-JB
    6. 17937
    Prev
    Next
    INDEX
    Explanations

    specific instances where something or someone "sticks to" a particular course of action or belief

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to adherence or commitment to principles or regulations

    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
    illion
    -0.85
    anooga
    -0.78
    ourage
    -0.76
    etheus
    -0.75
    ovember
    -0.75
    nesota
    -0.68
     pandemonium
    -0.68
    brance
    -0.68
    illions
    -0.67
    roximately
    -0.67
    POSITIVE LOGITS
     principles
    0.97
     orthodoxy
    0.94
     tradition
    0.93
     basics
    0.92
     traditions
    0.88
     traditional
    0.83
     fundamentals
    0.83
     principle
    0.82
     orthodox
    0.82
     monog
    0.81
    Activations Density 0.157%

    No Known Activations