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. 3-RES-JB
    6. 22200
    Prev
    Next
    INDEX
    Explanations

    the word "maximize" and related terms in contexts related to efficiency, improvement, or optimization

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to optimization and maximizing outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ker
    -0.92
    king
    -0.80
    soon
    -0.76
    intel
    -0.76
    lis
    -0.70
    neys
    -0.69
    bley
    -0.68
    worldly
    -0.68
    lust
    -0.68
    shit
    -0.67
    POSITIVE LOGITS
     maximizing
    1.00
    imize
    0.99
     maximize
    0.95
     maxim
    0.95
     minimize
    0.91
     minimizing
    0.87
     propri
    0.78
     minimized
    0.76
    urized
    0.75
     misunder
    0.75
    Activations Density 0.018%

    No Known Activations