© 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. 23858
    Prev
    Next
    INDEX
    Explanations

    references to taxation and tax-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to taxation

    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
    Found
    -0.78
    lime
    -0.76
    aque
    -0.71
    Lead
    -0.71
    found
    -0.68
    etting
    -0.68
    involved
    -0.66
     Pav
    -0.65
    feed
    -0.64
    lyn
    -0.63
    POSITIVE LOGITS
     taxing
    1.26
     taxed
    1.09
     taxable
    0.94
    payer
    0.90
     taxation
    0.89
     tax
    0.85
     levied
    0.85
     taxes
    0.85
     collectors
    0.84
    ©¶æ¥µ
    0.83
    Activations Density 0.009%

    No Known Activations