Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 834
    Prev
    Next
    INDEX
    Explanations

    code snippets related to Swift programming and memory management in Java

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    373
    +0.14
    0.7%
    384
    +0.11
    0.5%
    692
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.06
    158
    +0.11
    0.05
    255
    +0.10
    0.05
    Negative Logits
    76561
    -0.82
    Redd
    -0.81
    jri
    -0.80
    ansk
    -0.76
    angel
    -0.75
    atro
    -0.73
    Magikarp
    -0.73
    skirts
    -0.72
    egu
    -0.71
    papers
    -0.70
    POSITIVE LOGITS
     {
    1.03
     bool
    1.02
     Array
    0.98
     func
    0.95
     const
    0.93
    (){
    0.93
     enum
    0.92
     fn
    0.92
     struct
    0.91
     __
    0.90
    Activations Density 0.581%

    No Known Activations