© 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. 10-RES-JB
    11. 24289
    Prev
    Next
    INDEX
    Explanations

    economic indicators such as changes in prices, growth rates, and stock market movements

    oai_token-act-pair · gpt-3.5-turbo

    words related to changes in financial metrics or market movements

    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
    clus
    -0.80
    oros
    -0.67
    incerity
    -0.65
    onomic
    -0.64
    Í
    -0.63
     sar
    -0.62
    bred
    -0.62
    eday
    -0.61
    etary
    -0.60
    tta
    -0.57
    POSITIVE LOGITS
     sharply
    1.20
     marginally
    1.15
     slightly
    1.03
     significantly
    1.03
     substantially
    0.97
     markedly
    0.97
     considerably
    0.96
     brisk
    0.95
     steadily
    0.95
     ¥
    0.92
    Activations Density 0.111%

    No Known Activations