© 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. 1410
    Prev
    Next
    INDEX
    Explanations

    keywords related to shuffling, such as the action of shuffling items or people in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shuffle" and its variations

    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
    undai
    -0.78
    alez
    -0.77
    oded
    -0.75
    ourke
    -0.72
    acons
    -0.72
    ult
    -0.66
    ures
    -0.64
    onial
    -0.62
    elled
    -0.62
    yrinth
    -0.61
    POSITIVE LOGITS
     shuffle
    1.42
     shuff
    1.01
    jee
    1.01
     Solitaire
    0.96
    DAQ
    0.86
    uffle
    0.84
    board
    0.84
    cloth
    0.81
    lings
    0.79
     Doodle
    0.78
    Activations Density 0.015%

    No Known Activations