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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24439
    Prev
    Next
    INDEX
    Explanations

    words related to creativity and creation

    oai_token-act-pair · gpt-3.5-turbo

    references to creativity and creative entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reconciliation
    -0.71
    CLASSIFIED
    -0.66
     sounding
    -0.64
     prisoner
    -0.63
     dime
    -0.62
     tasting
    -0.62
     reinforcement
    -0.61
     chast
    -0.61
     recess
    -0.60
     Alph
    -0.59
    POSITIVE LOGITS
    es
    1.35
    iveness
    1.34
    ories
    1.34
    ivity
    1.24
    orial
    1.23
    ively
    1.20
    ibility
    1.19
    ors
    1.17
    ements
    1.17
    itives
    1.15
    Activations Density 0.074%

    No Known Activations