© 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 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. 0-RES-JB
    11. 1889
    Prev
    Next
    INDEX
    Explanations

    mentions of financial institutions, specifically banks

    oai_token-act-pair · gpt-3.5-turbo

    references to financial institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dyl
    -0.70
    cific
    -0.68
     additive
    -0.67
    advertising
    -0.66
    paralle
    -0.65
    DOM
    -0.64
    º
    -0.62
    humans
    -0.61
     ker
    -0.61
    meric
    -0.61
    POSITIVE LOGITS
     Bank
    3.93
    Bank
    3.06
    bank
    2.37
     bank
    2.35
     Banks
    2.05
     banks
    1.94
     Banking
    1.87
     banker
    1.70
     bankers
    1.67
     banking
    1.61
    Activations Density 0.011%

    No Known Activations