© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 21456
    Prev
    Next
    INDEX
    Explanations

    words related to maximizing or optimizing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to 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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ker
    -0.86
    tz
    -0.75
    pt
    -0.73
    bare
    -0.72
    lis
    -0.71
    bane
    -0.67
    die
    -0.67
    chest
    -0.67
    den
    -0.67
    ple
    -0.66
    POSITIVE LOGITS
     maximize
    1.29
     maximizing
    1.20
    imize
    1.12
     maxim
    1.03
     optimize
    0.97
     misunder
    0.89
     minimize
    0.88
    ĺħ
    0.88
     simultane
    0.85
    ilitarian
    0.83
    Activations Density 0.010%

    No Known Activations