© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9894
    Prev
    Next
    INDEX
    Explanations

    information related to a specific person or character, possibly from a sports or gaming context

    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
    +0.39
    2.1%
    756
    +0.13
    0.7%
    459
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.39
    -0.02
    598
    +0.13
    0.05
    559
    +0.09
    0.05
    Negative Logits
    Newsletter
    -0.74
     Watergate
    -0.66
     constitutional
    -0.65
     Guant
    -0.64
     nonviolent
    -0.63
     ministerial
    -0.59
     ballot
    -0.58
     telephone
    -0.58
    Britain
    -0.57
     referendum
    -0.57
    POSITIVE LOGITS
     luckily
    0.84
     haha
    0.74
     sadly
    0.73
    Luckily
    0.71
     however
    0.71
     alot
    0.69
     unfortunately
    0.69
    Thankfully
    0.69
     whats
    0.69
    prisingly
    0.69
    Activations Density 2.068%

    No Known Activations