© 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 1536
    9. 8-RES_FS1536-JB
    11. 1044
    Prev
    Next
    INDEX
    Explanations

    statistical data about various issues, such as child abuse and business trends

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    447
    +0.17
    0.8%
    576
    +0.12
    0.5%
    481
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    576
    +0.17
    0.08
    714
    +0.12
    0.09
    724
    +0.12
    0.14
    Negative Logits
     redacted
    -0.80
    mates
    -0.79
    DERR
    -0.74
     CLSID
    -0.73
     deducted
    -0.71
    wered
    -0.69
    tein
    -0.69
     violated
    -0.69
     waived
    -0.69
     oath
    -0.66
    POSITIVE LOGITS
     globalization
    1.17
     increasingly
    1.10
     trends
    1.01
     resurg
    0.98
     emerging
    0.98
     trend
    0.98
     consolidation
    0.97
     democrat
    0.96
     lately
    0.95
     worldwide
    0.93
    Activations Density 5.164%

    No Known Activations