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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 5676
    Prev
    Next
    INDEX
    Explanations

    mentions of tax-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to taxation and tax policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    board
    -0.73
    insk
    -0.70
     Kali
    -0.69
    uden
    -0.68
    mb
    -0.67
     Duo
    -0.67
    KI
    -0.66
    Ĥ¬
    -0.65
     Published
    -0.64
     Loaded
    -0.64
    POSITIVE LOGITS
     tax
    3.64
     Tax
    2.93
    tax
    2.89
    Tax
    2.84
     taxes
    2.72
     taxation
    2.38
     Taxes
    2.30
     taxed
    2.05
     taxing
    1.98
     taxable
    1.84
    Activations Density 0.025%

    No Known Activations