© 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. 2-RES-JB
    11. 17546
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial deductions such as deduct, deductible, depreciation, and deductions

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to tax deductions and financial calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hell
    -0.70
    anco
    -0.68
     Orange
    -0.67
    ounces
    -0.67
    ña
    -0.65
    igma
    -0.64
    cock
    -0.61
    RH
    -0.61
     Image
    -0.60
     Hoo
    -0.60
    POSITIVE LOGITS
     deduction
    1.23
     deductions
    1.20
     deduct
    1.15
     deducted
    1.08
     allowances
    0.93
     deductible
    0.93
     allowable
    0.92
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.92
     allowance
    0.91
    payer
    0.82
    Activations Density 0.010%

    No Known Activations