© 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 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. 0-RES-JB
    11. 13563
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to art or artistic activities

    oai_token-act-pair · gpt-3.5-turbo

    the keyword "ART" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flakes
    -0.72
     deposits
    -0.71
     Ske
    -0.68
     Siberian
    -0.66
     footh
    -0.65
     landslide
    -0.65
     lax
    -0.65
     Pyramid
    -0.64
     sl
    -0.64
     Curse
    -0.64
    POSITIVE LOGITS
    ART
    4.43
    arts
    2.39
    art
    1.99
     ART
    1.93
    arted
    1.59
    Art
    1.49
    ARD
    1.32
    ARC
    1.31
    HER
    1.31
    ATT
    1.30
    Activations Density 0.008%

    No Known Activations