© 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 · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19454
    Prev
    Next
    INDEX
    Explanations

    expressions related to taxes and financial payments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    59
    +0.09
    0.4%
    119
    +0.09
    0.4%
    688
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    552
    +0.09
    0.04
    59
    +0.09
    0.03
    604
    +0.09
    0.03
    Negative Logits
    bum
    -0.74
    ierre
    -0.74
    Aim
    -0.68
    è¯
    -0.67
    timer
    -0.65
    ogue
    -0.65
    ocent
    -0.64
    -----
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
     Moder
    -0.62
    POSITIVE LOGITS
     taxes
    1.16
     dues
    1.09
     dividends
    1.08
    checks
    1.07
     royalties
    1.04
     Taxes
    1.00
     debts
    0.99
     bills
    0.97
     salaries
    0.96
     owed
    0.96
    Activations Density 0.040%

    No Known Activations