© 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 12288
    9. 8-RES_FS12288-JB
    11. 1883
    Prev
    Next
    INDEX
    Explanations

    advice and strategies related to business and professional growth

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    +0.20
    0.9%
    5
    +0.11
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.20
    -0.04
    119
    +0.11
    0.05
    285
    +0.10
    0.04
    Negative Logits
    ported
    -0.79
    ufact
    -0.79
    atel
    -0.78
     Murdoch
    -0.74
    ocaust
    -0.74
     Tehran
    -0.72
     Kiev
    -0.71
     munitions
    -0.69
     Maduro
    -0.69
     Tasmania
    -0.67
    POSITIVE LOGITS
     mindfulness
    1.10
     subconscious
    0.99
     beginner
    0.98
     brainstorm
    0.98
     therapists
    0.94
     therapist
    0.94
     unconsciously
    0.93
     Technique
    0.91
     lear
    0.90
    learning
    0.89
    Activations Density 1.723%

    No Known Activations