© 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. 10-RES-JB
    11. 18667
    Prev
    Next
    INDEX
    Explanations

    phrases related to sudden appearance or emergence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "popping up" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    respect
    -0.72
    pport
    -0.68
    heid
    -0.65
    mma
    -0.64
     guid
    -0.62
    yet
    -0.61
    sports
    -0.61
    externalActionCode
    -0.60
     Respect
    -0.59
     Correspond
    -0.59
    POSITIVE LOGITS
     up
    1.12
     onto
    1.09
     forth
    1.03
     into
    1.01
     popped
    0.94
     spontaneously
    0.89
    ulates
    0.86
     INTO
    0.85
     out
    0.84
     ashore
    0.81
    Activations Density 0.052%

    No Known Activations