© 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. 5956
    Prev
    Next
    INDEX
    Explanations

    references to large amounts of money in the billions or trillions

    oai_token-act-pair · gpt-3.5-turbo

    references to large sums of money, specifically in the context of billions and trillions

    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
    DIT
    -0.74
    imen
    -0.69
    oras
    -0.61
    choes
    -0.60
    CHR
    -0.60
     flesh
    -0.60
    thel
    -0.59
    ¶æ
    -0.58
    dies
    -0.58
    chron
    -0.58
    POSITIVE LOGITS
    aires
    1.51
    aire
    1.41
    naire
    1.06
     Dollar
    1.01
    dollar
    0.98
    illion
    0.97
     dollars
    0.97
     dollar
    0.91
     Dollars
    0.75
    agy
    0.73
    Activations Density 0.011%

    No Known Activations