© 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. 0-RES-JB
    11. 7722
    Prev
    Next
    INDEX
    Explanations

    bank-related terms or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of financial institutions or banks

    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
     elements
    -0.62
     Meier
    -0.62
     atmosp
    -0.61
     Spartan
    -0.61
     custom
    -0.60
     Wolverine
    -0.60
    UG
    -0.60
    OSH
    -0.60
     tons
    -0.60
    ORN
    -0.59
    POSITIVE LOGITS
    bank
    4.52
    banks
    3.16
    Bank
    2.82
     Bank
    1.87
     bank
    1.84
     banks
    1.78
     Banks
    1.48
     Banking
    1.35
     banker
    1.34
     banking
    1.33
    Activations Density 0.012%

    No Known Activations