© 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. 8-RES-JB
    11. 22367
    Prev
    Next
    INDEX
    Explanations

    instances of monetary transactions or payments

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and associated financial terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.89
    yrinth
    -0.84
    aiman
    -0.73
    çİĭ
    -0.72
    ahime
    -0.71
    apons
    -0.69
    fy
    -0.69
     Canaveral
    -0.69
    eter
    -0.67
    ierre
    -0.66
    POSITIVE LOGITS
     dues
    1.20
     taxes
    1.10
     ransom
    1.07
     royalties
    1.04
     dividends
    1.02
     upfront
    0.99
     debts
    0.98
     penalty
    0.94
     bills
    0.94
     dearly
    0.93
    Activations Density 0.181%

    No Known Activations