© 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. 3-RES-JB
    11. 16361
    Prev
    Next
    INDEX
    Explanations

    ornamental words or phrases often related to design or decoration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ornamental or decorative objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mub
    -0.79
    Application
    -0.70
    MQ
    -0.69
    zero
    -0.67
    bies
    -0.65
     Redemption
    -0.65
     Dems
    -0.64
     tolerance
    -0.64
     Worldwide
    -0.63
    Zero
    -0.63
    POSITIVE LOGITS
    amental
    1.42
     orn
    1.09
    ith
    1.02
    atories
    0.94
    ormal
    0.90
    ifer
    0.89
    iane
    0.88
    ilater
    0.83
    ately
    0.81
    obal
    0.80
    Activations Density 0.020%

    No Known Activations