© 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. 1703
    Prev
    Next
    INDEX
    Explanations

    phrases about discussing ideas, beliefs, and theories

    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
    679
    +0.17
    0.8%
    640
    +0.15
    0.7%
    255
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.17
    0.15
    679
    +0.15
    0.14
    255
    +0.14
    0.12
    Negative Logits
    ascus
    -0.89
     earthqu
    -0.85
     awaited
    -0.84
     scheduled
    -0.81
     officially
    -0.74
     planned
    -0.74
    bang
    -0.74
    eteen
    -0.74
    abouts
    -0.73
     billed
    -0.72
    POSITIVE LOGITS
     Whereas
    1.61
     Hence
    1.59
     Therefore
    1.56
     Thus
    1.53
     Consequently
    1.50
     Often
    1.48
     Conversely
    1.45
     Sometimes
    1.44
     Ideally
    1.37
     Likewise
    1.36
    Activations Density 0.683%

    No Known Activations