© 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. 7131
    Prev
    Next
    INDEX
    Explanations

    financial amounts and details

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to pricing and financial information

    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
    hib
    -0.73
    warts
    -0.66
    minster
    -0.63
    inav
    -0.63
    ciplinary
    -0.62
    ĪĴ
    -0.62
    ownt
    -0.62
    hett
    -0.61
    eatures
    -0.61
    alkyrie
    -0.61
    POSITIVE LOGITS
     $
    2.49
    $
    1.95
     âĤ¬
    1.85
     £
    1.84
     ¥
    1.66
     $(
    1.54
     Rs
    1.53
     "$
    1.52
     $\
    1.49
     $$
    1.49
    Activations Density 0.108%

    No Known Activations