© 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. 11-RES-JB
    11. 2734
    Prev
    Next
    INDEX
    Explanations

    financial terms related to investments and securities

    oai_token-act-pair · gpt-3.5-turbo

    financial instruments and terms related to securities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alam
    -0.70
     Gast
    -0.69
     Compton
    -0.69
     Calais
    -0.69
    Lt
    -0.67
     Kenobi
    -0.66
     Ange
    -0.66
     Rath
    -0.64
    osta
    -0.63
     Guerrero
    -0.62
    POSITIVE LOGITS
     securities
    1.55
     holdings
    1.32
     liquidity
    1.28
     hed
    1.28
     Securities
    1.27
     ETF
    1.26
     issu
    1.24
     loans
    1.21
     mortgages
    1.21
     portfolios
    1.21
    Activations Density 0.239%

    No Known Activations