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

    Neuronpedia

    Jacobian LensNEW
    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 49152
    9. 8-RES_FS49152-JB
    11. 42937
    Prev
    Next
    INDEX
    Explanations

    references to universities and educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.14
    0.7%
    447
    +0.14
    0.6%
    31
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.14
    0.05
    359
    +0.14
    0.04
    53
    +0.10
    0.04
    Negative Logits
    ãĥ©
    -0.77
    worthiness
    -0.70
    è¦ļéĨĴ
    -0.69
    ãĥĨãĤ£
    -0.66
     smugglers
    -0.66
    ãĤ»
    -0.65
    к
    -0.64
    orders
    -0.62
    driven
    -0.61
    ãĥŀ
    -0.60
    POSITIVE LOGITS
     faculty
    1.43
     University
    1.36
     Students
    1.36
     students
    1.35
     Faculty
    1.34
    Students
    1.30
     graduate
    1.29
     athletics
    1.28
     undergrad
    1.28
     student
    1.26
    Activations Density 0.131%

    No Known Activations