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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16905
    Prev
    Next
    INDEX
    Explanations

    terms related to creativity

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of creativity

    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
    ighed
    -0.79
    abad
    -0.75
    akeru
    -0.73
    roe
    -0.72
    Downloadha
    -0.71
    astern
    -0.70
    osate
    -0.68
    upon
    -0.66
    latable
    -0.66
    late
    -0.66
    POSITIVE LOGITS
     creative
    1.02
     arts
    0.99
     genius
    0.94
     creat
    0.94
     commons
    0.94
     juices
    0.88
     creativity
    0.85
    creat
    0.83
     workspace
    0.83
     cout
    0.81
    Activations Density 0.012%

    No Known Activations