© 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. 2-RES-JB
    11. 19632
    Prev
    Next
    INDEX
    Explanations

    images, artwork, or paintings

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of painting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sg
    -0.81
    avez
    -0.79
    reme
    -0.74
    Ïī
    -0.74
    ornia
    -0.72
    cgi
    -0.72
    abad
    -0.71
    reek
    -0.71
    uli
    -0.70
    aspx
    -0.70
    POSITIVE LOGITS
     painting
    1.27
     painter
    1.18
     paintings
    1.18
     Painting
    1.00
     depicting
    0.99
    istry
    0.92
     artwork
    0.92
    brush
    0.89
     portraits
    0.88
    wright
    0.86
    Activations Density 0.011%

    No Known Activations