© 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. 4812
    Prev
    Next
    INDEX
    Explanations

    different currencies and related financial terms

    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
    287
    +0.12
    0.5%
    481
    +0.12
    0.5%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    673
    +0.12
    0.05
    546
    +0.12
    0.04
    497
    +0.11
    0.04
    Negative Logits
     listeners
    -0.79
    ODY
    -0.76
     audiences
    -0.70
    issance
    -0.69
    Cause
    -0.69
    istrate
    -0.69
    Scene
    -0.68
    Compl
    -0.68
    Offline
    -0.67
     observers
    -0.66
    POSITIVE LOGITS
     etc
    0.87
    etc
    0.84
     cass
    0.75
     Tart
    0.72
     banana
    0.72
     Mongol
    0.71
     rye
    0.71
     Gamma
    0.71
     Titan
    0.71
     chlor
    0.71
    Activations Density 0.240%

    No Known Activations