© 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 24576
    9. 8-RES_FS24576-JB
    11. 1714
    Prev
    Next
    INDEX
    Explanations

    technical features and reviews related to performance and components of electronic devices

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    +0.21
    1.0%
    255
    +0.11
    0.5%
    664
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.21
    -0.03
    255
    +0.11
    0.04
    326
    +0.10
    0.07
    Negative Logits
     Citizenship
    -0.72
     founding
    -0.72
     Books
    -0.70
     scapego
    -0.69
     Founding
    -0.68
     Pension
    -0.68
    ropolitan
    -0.68
    âĢİ
    -0.67
     proclamation
    -0.66
     Collective
    -0.66
    POSITIVE LOGITS
     latency
    1.12
     accur
    1.12
     fps
    1.10
    fps
    1.08
     throughput
    1.08
     overcl
    1.08
     airflow
    1.02
     smoother
    1.02
     speeds
    1.01
     responsiveness
    1.00
    Activations Density 0.750%

    No Known Activations