© 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. 8-RES-JB
    11. 536
    Prev
    Next
    INDEX
    Explanations

    word combinations related to economic bubbles

    oai_token-act-pair · gpt-3.5-turbo

    references to "bubble" in various contexts, particularly economic or financial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ives
    -0.95
    IVES
    -0.92
    nesota
    -0.87
    Ģ
    -0.82
    aves
    -0.75
    IVE
    -0.72
    OTO
    -0.71
    FTWARE
    -0.70
    avement
    -0.69
    IFE
    -0.69
    POSITIVE LOGITS
    bub
    1.03
     bubble
    1.00
     bubbles
    0.98
    ulent
    0.96
     inflated
    0.95
     gum
    0.91
     burst
    0.90
     bursting
    0.89
     popped
    0.87
    wrap
    0.81
    Activations Density 0.051%

    No Known Activations