© 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. 4-RES-JB
    11. 1521
    Prev
    Next
    INDEX
    Explanations

    words related to decoration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to decoration and ornamentation

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

    No Comments

    Negative Logits
    uge
    -0.72
     Rage
    -0.67
    yah
    -0.66
    demand
    -0.63
    oner
    -0.63
     FTA
    -0.62
    SPA
    -0.62
    shi
    -0.61
     translated
    -0.60
    Scott
    -0.60
    POSITIVE LOGITS
     decoration
    1.38
     decorations
    1.32
     decor
    1.06
     motif
    0.95
     decorated
    0.92
    ments
    0.85
     ribbon
    0.81
     Ribbon
    0.81
     artwork
    0.80
     ornament
    0.79
    Activations Density 0.021%

    No Known Activations