© 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 3072
    9. 8-RES_FS3072-JB
    11. 216
    Prev
    Next
    INDEX
    Explanations

    discussions related to beliefs, reasoning, and self-reflection

    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
    255
    +0.15
    0.7%
    640
    +0.15
    0.7%
    679
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.15
    0.21
    255
    +0.15
    0.17
    679
    +0.14
    0.19
    Negative Logits
    ascus
    -0.84
    abouts
    -0.79
     earthqu
    -0.77
     awaited
    -0.77
     billed
    -0.77
     officially
    -0.75
    ported
    -0.74
     mailed
    -0.74
     scheduled
    -0.73
    eteen
    -0.73
    POSITIVE LOGITS
     Therefore
    1.69
     Hence
    1.61
     Whereas
    1.58
     Thus
    1.53
     Consequently
    1.53
     Ideally
    1.52
     Conversely
    1.50
     Otherwise
    1.46
     Often
    1.44
    Therefore
    1.43
    Activations Density 1.827%

    No Known Activations