© 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. 11-RES-JB
    11. 20472
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "boom"

    oai_token-act-pair · gpt-3.5-turbo

    references to "bubbles" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Episcopal
    -0.63
     neutrality
    -0.62
     impunity
    -0.61
    éĸ
    -0.60
     à¨
    -0.59
     Millennium
    -0.58
     accounting
    -0.58
     specificity
    -0.58
     commem
    -0.57
    CLASSIFIED
    -0.57
    POSITIVE LOGITS
    ogie
    1.44
    oby
    1.31
    gey
    1.27
    omer
    1.21
    ister
    1.15
    pping
    1.15
    oms
    1.11
    quet
    1.11
    zos
    1.09
    zo
    1.08
    Activations Density 0.031%

    No Known Activations