© 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. 4-RES-JB
    11. 10038
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions like repaying debts or loans

    oai_token-act-pair · gpt-3.5-turbo

    terms related to payment and debt obligations

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

    No Comments

    Negative Logits
     Butterfly
    -0.81
    Dutch
    -0.71
    女
    -0.70
    soft
    -0.69
    =-=-=-=-=-=-=-=-
    -0.68
    ovie
    -0.66
    alt
    -0.66
    ismo
    -0.65
     Bav
    -0.65
    ulhu
    -0.64
    POSITIVE LOGITS
     repay
    1.28
     repayment
    1.25
     repaid
    1.09
    owship
    1.02
     forgiveness
    0.90
     forgiven
    0.90
     payments
    0.84
     refunds
    0.80
     loan
    0.79
     favorably
    0.77
    Activations Density 0.011%

    No Known Activations