© 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 · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 10375
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms and indicators

    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
    373
    +0.11
    0.5%
    668
    +0.11
    0.5%
    448
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.11
    0.03
    600
    +0.11
    0.03
    21
    +0.10
    0.03
    Negative Logits
    sonian
    -0.72
    Gate
    -0.70
     Silence
    -0.70
     trolls
    -0.69
    dream
    -0.68
    natureconservancy
    -0.67
     trials
    -0.66
    rovers
    -0.66
    ????????
    -0.66
    ealous
    -0.65
    POSITIVE LOGITS
     GDP
    1.60
     income
    1.29
     Income
    1.18
     incomes
    1.17
     Gross
    1.17
     earnings
    1.17
     gross
    1.12
    adjusted
    1.07
     CPI
    1.07
     adjusted
    1.06
    Activations Density 0.222%

    No Known Activations