© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 4897
    Prev
    Next
    INDEX
    Explanations

    terms related to taxation

    oai_token-act-pair · gpt-3.5-turbo

    references to taxation and its various implications

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

    No Comments

    Negative Logits
    ity
    -0.78
    aque
    -0.75
    lime
    -0.73
    éĹĺ
    -0.68
    erd
    -0.67
    sky
    -0.67
    Found
    -0.67
    syn
    -0.63
    chat
    -0.63
     Sever
    -0.63
    POSITIVE LOGITS
     taxing
    1.21
     taxed
    0.98
    payer
    0.93
    ©¶æ¥µ
    0.88
     levied
    0.87
     taxation
    0.86
     taxes
    0.83
     taxable
    0.79
     peanuts
    0.77
    ptives
    0.76
    Activations Density 0.014%

    No Known Activations