Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 10035
    Prev
    Next
    INDEX
    Explanations

    words associated with maximizing or optimization

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of maximizing outcomes or benefits

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

    No Comments

    Negative Logits
    ker
    -1.01
    king
    -0.86
    soon
    -0.77
    kers
    -0.76
    intel
    -0.75
    worldly
    -0.75
    lis
    -0.69
    shit
    -0.68
    bro
    -0.68
    lust
    -0.68
    POSITIVE LOGITS
     maximizing
    1.12
    imize
    1.05
     maximize
    1.03
     minimize
    0.92
     maxim
    0.90
     minimizing
    0.89
     propri
    0.83
    imal
    0.79
     optimize
    0.76
    urized
    0.74
    Activations Density 0.029%

    No Known Activations