© 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. 11-RES-JB
    11. 3518
    Prev
    Next
    INDEX
    Explanations

    phrases related to sudden appearances or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pop" and its variations, particularly in contexts related to appearances or occurrences

    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
    yet
    -0.69
    partial
    -0.68
    pport
    -0.63
    mand
    -0.60
    venge
    -0.60
     guid
    -0.60
    ña
    -0.59
    rang
    -0.59
    sen
    -0.59
     Correspond
    -0.58
    POSITIVE LOGITS
     forth
    1.15
     onto
    1.08
     into
    1.00
     up
    0.93
     INTO
    0.91
    ulates
    0.88
     bubbles
    0.87
     awake
    0.87
     spontaneously
    0.87
     popped
    0.87
    Activations Density 0.092%

    No Known Activations