© 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 12288
    9. 8-RES_FS12288-JB
    11. 10409
    Prev
    Next
    INDEX
    Explanations

    information related to economic analysis, particularly cost-saving measures and financial impact assessments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    86
    +0.11
    0.5%
    51
    +0.10
    0.5%
    619
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.11
    0.07
    570
    +0.10
    0.03
    495
    +0.10
    0.06
    Negative Logits
     Lists
    -0.73
    ese
    -0.72
     selection
    -0.66
    Winged
    -0.65
     Gamer
    -0.63
     CTRL
    -0.63
     Password
    -0.63
     selections
    -0.62
    dit
    -0.61
    oplan
    -0.60
    POSITIVE LOGITS
     annually
    1.04
    -$
    0.86
     savings
    0.84
     (£
    0.84
     incurred
    0.81
     shortfall
    0.80
     aver
    0.80
     attributable
    0.79
     crore
    0.79
     adversely
    0.76
    Activations Density 0.521%

    No Known Activations