© 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. 9-RES-JB
    11. 16633
    Prev
    Next
    INDEX
    Explanations

    words related to financial matters such as payment, overpayment, subscription, representation, investment, and consumption

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial transactions and economic evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adr
    -0.67
     Abbas
    -0.60
    accompan
    -0.60
     slit
    -0.60
     Cumm
    -0.60
     Chr
    -0.58
    block
    -0.57
    Brave
    -0.57
    Beat
    -0.56
    upper
    -0.55
    POSITIVE LOGITS
    xual
    1.06
    ements
    0.78
    ealous
    0.75
    phrine
    0.73
    imate
    0.73
    mson
    0.71
    dden
    0.70
    adows
    0.70
     expectations
    0.67
    ukong
    0.67
    Activations Density 0.138%

    No Known Activations