© 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. 11-RES-JB
    11. 7594
    Prev
    Next
    INDEX
    Explanations

    descriptions related to creating artwork

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to artistic creation and design processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĹ¼
    -0.81
    Ranked
    -0.80
    ilege
    -0.79
    erate
    -0.78
    Reason
    -0.76
    Weak
    -0.75
    Prosecut
    -0.73
    Agg
    -0.72
    competitive
    -0.71
    ghazi
    -0.71
    POSITIVE LOGITS
     sculptures
    1.74
     paintings
    1.73
     sculpture
    1.65
     mural
    1.65
     drawings
    1.64
     illustrations
    1.58
     artwork
    1.56
     portraits
    1.55
     sketches
    1.49
     painting
    1.45
    Activations Density 0.662%

    No Known Activations