© 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 EvalsExportsinterp-engineNEWAPI 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. 15777
    Prev
    Next
    INDEX
    Explanations

    information related to economic conditions and 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
    +0.13
    0.6%
    608
    +0.10
    0.5%
    749
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.03
    749
    +0.10
    0.02
    608
    +0.10
    0.03
    Negative Logits
    çīĪ
    -0.89
    æ³
    -0.81
    Planet
    -0.78
    wered
    -0.78
    iors
    -0.74
    soever
    -0.69
    thing
    -0.69
    ices
    -0.68
    Jess
    -0.67
    fuck
    -0.67
    POSITIVE LOGITS
    efficiency
    1.11
     popularity
    1.05
     incidence
    0.99
    effic
    0.94
     revenues
    0.92
     intensity
    0.90
     revenue
    0.90
     prevalence
    0.90
     concentration
    0.87
     competitiveness
    0.86
    Activations Density 0.068%

    No Known Activations