© 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. 10715
    Prev
    Next
    INDEX
    Explanations

    numerical data related to financial figures like income, expenses, and revenues

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values associated with income and financial statistics

    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
     fronts
    -0.68
     princ
    -0.61
     apartheid
    -0.56
     strugg
    -0.55
     disapp
    -0.55
     Rhodes
    -0.51
     toes
    -0.51
     scrut
    -0.51
     Collider
    -0.50
     Wid
    -0.50
    POSITIVE LOGITS
    00
    1.19
     million
    1.03
    -$
    1.00
     billion
    1.00
    00000
    0.98
    million
    0.96
    billion
    0.92
    50
    0.90
    bn
    0.87
     MILL
    0.84
    Activations Density 0.088%

    No Known Activations