© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15633
    Prev
    Next
    INDEX
    Explanations

    updates and emerging details in news stories

    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
    665
    +0.11
    0.5%
    317
    +0.10
    0.4%
    216
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.05
    98
    +0.10
    0.05
    79
    +0.09
    0.04
    Negative Logits
    tein
    -0.78
     1962
    -0.67
     1976
    -0.67
    agall
    -0.66
     1961
    -0.65
    advant
    -0.64
     1978
    -0.64
     1964
    -0.63
    vec
    -0.63
    ade
    -0.63
    POSITIVE LOGITS
     updates
    1.26
     details
    1.05
    catentry
    1.01
     Updates
    1.00
    soon
    0.99
     update
    0.99
     TBA
    0.97
     developments
    0.94
     TBD
    0.93
     soon
    0.91
    Activations Density 0.315%

    No Known Activations