© 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. 11-RES-JB
    11. 3538
    Prev
    Next
    INDEX
    Explanations

    mentions of art installations or exhibitions

    oai_token-act-pair · gpt-3.5-turbo

    references to art installations and architectural projects

    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
    amacare
    -0.90
     ObamaCare
    -0.83
    ghazi
    -0.82
     retarded
    -0.79
     idiots
    -0.78
    cfg
    -0.76
     NASCAR
    -0.76
     whining
    -0.75
    ciating
    -0.74
     annoying
    -0.73
    POSITIVE LOGITS
     sculpture
    1.55
     exhibition
    1.54
     exhibitions
    1.51
     sculptures
    1.43
     curated
    1.39
     mural
    1.33
     curator
    1.31
     Frie
    1.29
     Exhibition
    1.29
     gallery
    1.29
    Activations Density 0.721%

    No Known Activations