© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3-RES-JB
    11. 1887
    Prev
    Next
    INDEX
    Explanations

    words related to waffles

    oai_token-act-pair · gpt-3.5-turbo

    references to "waffles"

    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
     Uz
    -0.75
    uality
    -0.68
     skelet
    -0.65
    GV
    -0.63
    ual
    -0.62
     Known
    -0.62
    ccording
    -0.62
     fertility
    -0.61
     Gut
    -0.60
     Kut
    -0.59
    POSITIVE LOGITS
    affle
    1.01
    poon
    0.91
    vine
    0.89
    iliate
    0.83
    azaar
    0.80
    affles
    0.77
    poons
    0.77
    redd
    0.77
    eries
    0.77
    arthed
    0.76
    Activations Density 0.015%

    No Known Activations