Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10899
    Prev
    Next
    INDEX
    Explanations

    phrases related to tax systems and financial regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to tax systems, specifically Goods and Services Tax (GST) and Value Added Tax (VAT)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ange
    -0.93
    lihood
    -0.73
    Acknowled
    -0.72
    ppel
    -0.72
    DragonMagazine
    -0.71
    ______
    -0.71
     Schne
    -0.71
     Roe
    -0.70
     Arbor
    -0.70
    Ber
    -0.68
    POSITIVE LOGITS
     VAT
    1.19
     GST
    0.98
    ©¶æ¥µ
    0.90
     levied
    0.86
     collectors
    0.84
     expenditure
    0.84
    ategory
    0.81
     excise
    0.81
    SIM
    0.77
     Revenue
    0.75
    Activations Density 0.008%

    No Known Activations