© 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. 6238
    Prev
    Next
    INDEX
    Explanations

    instances of the word "waving"

    oai_token-act-pair · gpt-3.5-turbo

    instances of waving or gestures related to signaling or expression

    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
    IVES
    -0.76
    unker
    -0.66
    Ranked
    -0.66
    ocker
    -0.65
    heid
    -0.62
    ãĥ¯ãĥ³
    -0.61
    ateral
    -0.61
    ulz
    -0.61
    oyal
    -0.60
    sen
    -0.60
    POSITIVE LOGITS
     waving
    1.06
    pole
    0.96
     goodbye
    0.96
     waved
    0.94
    boat
    0.80
    bands
    0.77
    glers
    0.76
    lasses
    0.76
    wheel
    0.75
    uay
    0.75
    Activations Density 0.004%

    No Known Activations