© 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. 21375
    Prev
    Next
    INDEX
    Explanations

    words related to creativity; especially focused on the concept of creating something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "create" and related forms

    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
    HEAD
    -0.75
     SHARES
    -0.72
     Britann
    -0.70
     Sahara
    -0.68
     Heads
    -0.67
     Mandatory
    -0.67
    EGA
    -0.64
     Peninsula
    -0.62
     Doctrine
    -0.62
     Cameroon
    -0.61
    POSITIVE LOGITS
    creat
    1.47
    Creat
    1.05
    ivity
    0.93
    furt
    0.93
    uration
    0.89
     creat
    0.88
    esy
    0.86
    smanship
    0.85
    ãĥ¼ãĥĨãĤ£
    0.85
    issance
    0.85
    Activations Density 0.008%

    No Known Activations