© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 7097
    Prev
    Next
    INDEX
    Explanations

    terms related to tax systems, particularly focusing on GST (Goods and Services Tax) and VAT (Value-Added Tax)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to taxation and fiscal policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ange
    -0.88
     Schne
    -0.87
    Ber
    -0.82
    é¾įå
    -0.76
    Sequ
    -0.76
     Sie
    -0.75
     Fra
    -0.74
    PsyNetMessage
    -0.73
    apple
    -0.72
    Problem
    -0.72
    POSITIVE LOGITS
     VAT
    1.34
     GST
    1.18
     excise
    0.95
    olkien
    0.86
     expenditure
    0.85
     evasion
    0.85
     rebate
    0.83
    ©¶æ¥µ
    0.82
     levied
    0.81
     tax
    0.81
    Activations Density 0.011%

    No Known Activations