© 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. 19542
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic or financial trends

    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
    362
    +0.11
    0.5%
    5
    +0.10
    0.5%
    608
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.03
    692
    +0.10
    0.02
    647
    +0.09
    0.02
    Negative Logits
    ettle
    -0.77
    deal
    -0.67
    bra
    -0.67
    itution
    -0.67
     violates
    -0.66
    aven
    -0.66
    iltr
    -0.65
    ran
    -0.65
     originated
    -0.65
    wrong
    -0.64
    POSITIVE LOGITS
     Geh
    0.79
     another
    0.76
     vigorous
    0.74
     an
    0.72
     dozens
    0.71
     a
    0.70
     assurances
    0.70
     additional
    0.69
     countless
    0.69
     numerous
    0.69
    Activations Density 0.079%

    No Known Activations