© 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. 2265
    Prev
    Next
    INDEX
    Explanations

    financial terms and numbers related to business and investments

    oai_token-act-pair · gpt-3.5-turbo

    indicators of uncertainty or variability in economic contexts

    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
    awei
    -0.69
     citiz
    -0.68
    wolves
    -0.68
    minist
    -0.67
    aturdays
    -0.67
    senal
    -0.65
    aditional
    -0.63
     newcom
    -0.61
     eleph
    -0.61
     nomine
    -0.60
    POSITIVE LOGITS
    Therefore
    0.80
    Yet
    0.75
    Indeed
    0.73
    Plus
    0.71
     Imran
    0.71
    Thankfully
    0.71
     Franch
    0.70
    Especially
    0.69
    Scroll
    0.69
    Research
    0.68
    Activations Density 0.428%

    No Known Activations