© 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. 8861
    Prev
    Next
    INDEX
    Explanations

    instructions or explanations related to technical tasks or projects

    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
    87
    +0.37
    1.9%
    384
    +0.10
    0.5%
    738
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.37
    -0.02
    45
    +0.10
    0.04
    384
    +0.09
    0.04
    Negative Logits
    Democratic
    -0.75
    Senate
    -0.71
     Democratic
    -0.70
    Gov
    -0.69
    ublic
    -0.68
     Democrat
    -0.67
    Republic
    -0.66
    Republican
    -0.65
    gov
    -0.64
    nesty
    -0.63
    POSITIVE LOGITS
     lasers
    0.92
     teleportation
    0.89
     teleport
    0.88
     arrows
    0.88
     grap
    0.86
     combinations
    0.86
     triangles
    0.85
     curved
    0.84
     geometric
    0.84
     curves
    0.83
    Activations Density 0.760%

    No Known Activations