© 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. 3083
    Prev
    Next
    INDEX
    Explanations

    information related to event logistics and procedures

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    640
    +0.32
    1.6%
    160
    +0.14
    0.7%
    442
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.32
    0.13
    107
    +0.14
    0.11
    442
    +0.14
    0.11
    Negative Logits
     championed
    -0.81
     radical
    -0.79
     spir
    -0.79
     increasingly
    -0.78
     sustained
    -0.77
     feared
    -0.77
     revol
    -0.77
     unstoppable
    -0.74
     sculpt
    -0.74
     escaping
    -0.73
    POSITIVE LOGITS
    Conclusion
    1.74
    Lastly
    1.74
    Finally
    1.67
    Additionally
    1.57
    Example
    1.54
    Also
    1.53
    Regarding
    1.52
    If
    1.51
    Important
    1.50
    Questions
    1.47
    Activations Density 0.322%

    No Known Activations