© 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. 18662
    Prev
    Next
    INDEX
    Explanations

    financial terms and names related to economic events

    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
    447
    +0.14
    0.6%
    304
    +0.10
    0.4%
    670
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.04
    146
    +0.10
    0.03
    304
    +0.10
    0.03
    Negative Logits
    iple
    -0.73
    antry
    -0.71
    reads
    -0.69
     Allaah
    -0.69
    olon
    -0.68
    oute
    -0.68
     Cait
    -0.67
    inct
    -0.66
    ãĥ¼ãĥ³
    -0.65
     YPG
    -0.65
    POSITIVE LOGITS
     liquidity
    1.25
     bailout
    1.24
     banks
    1.22
     lenders
    1.14
     loans
    1.14
     banking
    1.11
     bankers
    1.08
     bankrupt
    1.07
     bankruptcy
    1.07
     borrowers
    1.07
    Activations Density 0.098%

    No Known Activations